Laser therapy device energy precision adjustment method and device

Abstract

The present invention relates to the field of electrical digital data processing, and more specifically, to a method and device for adjusting the energy accuracy of a laser therapeutic device. The method comprises: constructing an energy data set; calculating the noise level of target data, and correcting the noise performance level to obtain a noise level correction value; obtaining a preset number of segmentation points, and calculating the preferred degree of the marked points; taking the segmentation point corresponding to the maximum preferred degree as the optimal segmentation point, and obtaining the final segmentation tree and the abnormal score of each energy output data according to the optimal segmentation point, and taking the energy output data with an abnormal score greater than a preset threshold as an abnormal point to complete the energy adjustment of the laser therapeutic device. Through the technical solution of the present invention, the accuracy of the use parameters of the laser therapeutic device can be improved, the treatment effect can be improved, and the safety of patients can be guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of electronic digital data processing, and more specifically, to a method and device for adjusting the energy accuracy of a laser therapeutic device. Background Art

[0002] Laser medical technology is an advanced medical method that uses the specific wavelength, energy and action time of lasers to treat diseases. With the development of laser treatment technology, laser therapeutic devices have shown significant therapeutic effects and advantages in the fields of ophthalmic surgery, skin treatment, tumor resection, etc. The precision and minimally invasive nature of lasers make them an indispensable part of modern medical technology. In the laser medical process, precise control of energy is the key to ensuring treatment effects and patient safety. Excessive energy fluctuations may cause tissue damage, while too low energy fluctuations may affect the treatment effect. Therefore, the precise energy output of laser equipment is crucial to medical safety and effectiveness.

[0003] The existing Chinese patent application document with publication number CN116959696A discloses a data processing method and device based on a laser therapy device, the method comprising: constructing a time-series medical database containing multiple treatment strategy classification results, parameters including operation mode, usage intensity and usage time; constructing a first model, the first model is a pre-trained deep learning model, using the database to train the first model to obtain a second model, the second model is a pre-trained deep learning model for treatment strategy classification; creating a data queue for the target user, allocating model storage space to store the target user's historical data and the target user's second model; performing incremental training on the second model, generating and outputting a recommendation list containing the treatment strategy classification results.

[0004] However, the laser therapy device will be accompanied by some noise in its energy output, resulting in fluctuations in the energy output. The above application document did not process the data of the laser therapy device during the data collection process, and the accuracy of the usage parameters of the laser therapy device obtained through training may be low. Summary of the invention

[0005] In order to solve the problem of low accuracy of the use parameters of a laser therapeutic apparatus, the present invention proposes a method and a device for adjusting the energy accuracy of a laser therapeutic apparatus.

[0006] In a first aspect, the present invention discloses a method for adjusting the energy accuracy of a laser therapeutic device, comprising: acquiring energy output data of the laser therapeutic device according to a preset sampling interval to construct an energy data set; taking any energy output data as target data, calculating the noise level of the target data, correcting the noise performance level to obtain a noise level correction value, traversing the energy data set, and obtaining a correction value sequence; acquiring a preset number of segmentation points, taking any segmentation point as a marking point, recursively segmenting the energy data set using the marking point, constructing the path length of each energy output data in the segmentation tree after segmentation as a path sequence, and calculating the preferred degree of the marking point; traversing all segmentation points, taking the segmentation point corresponding to the maximum preferred degree as the optimal segmentation point, obtaining the final segmentation tree and the abnormal score of each energy output data according to the optimal segmentation point, and taking the energy output data with an abnormal score greater than a preset threshold as an abnormal point to complete the energy adjustment of the laser therapeutic device; wherein the preferred degree satisfies the relationship: , Indicates The preference of the split point, Indicates A path sequence of split points, Indicates The corrected value sequence of the split points, Indicates similarity, Indicates the adjustment parameter.

[0007] The noise level of each data point is calculated and then the noise is corrected. Through recursive segmentation and optimization calculation, not only the accuracy of anomaly detection is improved, but also the anomaly detection process is optimized by dynamically adjusting the segmentation point, making the energy adjustment of the laser therapy device more accurate and efficient. In addition, the introduction of similarity measurement and adjustment parameters further enhances the adaptability and robustness of data changes in different noise environments, thereby ensuring the stability and safety of energy output during laser treatment.

[0008] Preferably, calculating the noise level includes: constructing a coordinate system with sampling time as the horizontal axis and the value of the energy output data as the vertical axis, recording two energy output data adjacent to the target data as a left reference point and a right reference point in the order of sampling time, and respectively obtaining a first straight line passing through the left reference point and the target data, a second straight line passing through the right reference point and the target data, and a third straight line passing through the target data and perpendicular to the horizontal axis; taking the angle between the first straight line and the third straight line as the first angle, taking the angle between the second straight line and the third straight line as the second angle, the first angle and the second angle being less than or equal to a right angle; calculating the angle sum of the first angle and the second angle, and taking the sine value of the difference between the angle sum and the straight angle as the noise level.

[0009] It can intuitively identify mutations or anomalies in energy data sets and evaluate their stability by measuring the geometric relationship between energy output data. When the sum of the two angles is close to 180 degrees, it indicates that the target data point is basically in a straight line with the left and right reference points, that is, the noise level is low; on the contrary, if the sum of the angles is far from 180 degrees, it indicates that the target data point may be an anomaly.

[0010] Preferably, when the target data is located at the beginning or the end of the energy data set, the noise level is zero.

[0011] Preferably, calculating the noise level further comprises: calculating an average energy output value of the energy data set, and normalizing the Euclidean distance between the energy output value of the target data and the average energy output value as the noise level.

[0012] When analyzing the Euclidean distance between the target data in the energy data set and the average energy output value of the energy data set, the degree of deviation between the target data and the average level of the entire energy data set is quantified, so as to more accurately judge the noise level of the target data.

[0013] Preferably, calculating the noise level correction value includes: constructing an influence window with the target data as the midpoint and a preset length as the window size, and taking the energy output data other than the target data in the influence window as the influence data; performing curve fitting on the influence window using the least squares method; and the noise level correction value satisfies the relationship:

[0014] , Indicates energy output data The noise level correction value is Indicates energy output data The noise level, Indicates The fitting value of the data on the curve is affected by Indicates The energy output value that affects the data, Indicates the total number of impact data, represents the hyperbolic tangent function.

[0015] It is possible to take into account the overall trend and deviation of the target data point, thereby more accurately correcting the degree of noise. The use of the hyperbolic tangent function makes the correction value give higher weight to larger deviations, enhancing the sensitivity to abnormal changes.

[0016] Preferably, calculating the noise level correction value also includes: synchronously acquiring a power data set according to a preset sampling interval of the energy data set, and taking the power value corresponding to the target data as the target power; calculating the mean of the distance between each power value in the power data set and the target power, and taking the normalized mean as the weight and multiplying the noise level as the noise level correction value.

[0017] The change in power is positively correlated with the change in energy output, and using the normalized mean as the weight can globally consider the outliers of the target data in the power data set, thereby increasing the accuracy of the correction of the noise level.

[0018] Preferably, the abnormal points are removed, and the energy data set is supplemented by cubic spline interpolation to obtain a denoised energy data set, thereby completing the energy adjustment of the laser therapy device.

[0019] In a second aspect, the present invention discloses a device for adjusting the energy accuracy of a laser therapy device, comprising: a processor; and a memory, wherein the memory stores computer instructions, and when the computer instructions are executed by the processor, the device executes the above-mentioned method for adjusting the energy accuracy of the laser therapy device.

[0020] Beneficial effects of the present invention:

[0021] The accuracy of the laser therapy instrument's operating parameters is improved, and the stability and accuracy of the energy output are improved to ensure the safety and effectiveness of the treatment process. In this way, the performance of the laser therapy instrument can be better controlled, and treatment deviations caused by equipment noise or other interference factors can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0023] Figure 1 It is a flow chart of a method for adjusting energy accuracy of a laser therapeutic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0025] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0026] The present invention provides a method for adjusting the energy accuracy of a laser therapeutic device. Figure 1 As shown, the method for adjusting the energy accuracy of the laser therapy device includes steps S1 to S4, which are described in detail below.

[0027] S1, obtaining energy output data of the laser therapy device according to a preset sampling interval and constructing an energy data set.

[0028] It should be noted that the energy accuracy adjustment of laser therapy devices generally includes: measurement and control of power or energy output, setting of technical parameters and software control, etc. Among them, the setting of technical parameters includes power, output mode, laser wavelength, etc. These parameters have a direct impact on energy accuracy; modern laser therapy equipment is usually equipped with an intelligent control system that can control parameters such as power, pulse width, frequency, etc. to achieve precise energy output.

[0029] The noise that may exist in the energy output data of laser therapy devices includes relative intensity noise, acoustic noise and technical noise. Among them, relative intensity noise is a parameter of laser light intensity fluctuation, which is manifested as the wavelength (energy) of the photons emitted by the laser is not constant; acoustic noise is the noise generated in the excimer laser myopia treatment device, which may approach or exceed the prescribed allowable range and may interfere with the patient's cooperation with the operation; technical noise comes from factors such as the additional noise of the pump light source, the swing of the laser resonant cavity, and temperature fluctuations.

[0030] In one embodiment, during the operation of the laser therapy device, the energy output data is collected by a high-precision photoelectric energy meter. For example, an Ophir NOVA II laser power energy meter is used, which can provide accurate power and energy measurements and is suitable for lasers of various wavelengths and power levels. Exemplarily, the preset sampling interval is set to 2kHz, which means that 2000 energy output data can be collected per second, so that the energy output changes of the laser therapy device during operation can be analyzed and recorded in detail.

[0031] The energy output data obtained at multiple consecutive sampling intervals are constructed as an energy data set.

[0032] S2, calculate the noise level of the target data, correct the noise level to obtain a noise level correction value, traverse the energy data set, and obtain a correction value sequence.

[0033] It should be noted that when the photoelectric energy meter collects the energy output data of the laser therapy device, interference from the surrounding environment, such as the movement of the operator, the mechanical vibration of the equipment itself, temperature changes, power supply stability, etc., may become the source of noise and affect the accuracy of the energy output data. Such noise manifests itself as mutation in the change of energy output data. Therefore, the degree of noise can be calculated using the mutation of the energy output data.

[0034] In one embodiment, a coordinate system is constructed with the sampling time as the horizontal axis and the value of the energy output data as the vertical axis, and the two energy output data adjacent to the target data are recorded as the left reference point and the right reference point in order of the sampling time, and a first straight line passing through the left reference point and the target data, a second straight line passing through the right reference point and the target data, and a third straight line passing through the target data and perpendicular to the horizontal axis are obtained respectively.

[0035] The angle between the first straight line and the third straight line is taken as the first angle, the angle between the second straight line and the third straight line is taken as the second angle, and the first angle and the second angle are less than or equal to a right angle; the angle sum of the first angle and the second angle is calculated, and the sine value of the difference between the angle sum and the straight angle is taken as the noise degree.

[0036] When the target data is located at the beginning or end of the energy data set, the noise level is 0.

[0037] The noise level satisfies the relationship:

[0038] , Indicates energy output data The noise level, represents the first angle, represents the second angle, represents a straight angle, Represents the total number of energy output data in the energy dataset, represents the sine value, , .

[0039] or Respectively represent energy output data Located at the beginning or end of the energy data set, the energy output data It is impossible to find two adjacent reference points, that is, the noise level is 0. Compare the sum of the first angle and the second angle with the straight angle. When the sum of the two angles is close to the straight angle, that is, 180 degrees, the three continuous energy output data of the surface approach a straight line. At this time, the energy output data The mutation rate is low.

[0040] It should be noted that during the operation of the laser therapy device, there are some normal data changes that lead to fluctuations in the energy output data. For example, artificial changes in the output of laser energy will cause changes in the energy data set. If only the noise level is calculated, normal data changes will be detected as noise points. Therefore, the calculated noise level needs to be corrected. Considering that normal data changes usually present a smooth change trend and no sudden changes occur, the smoothness of the energy output data within the impact window can be used to correct the noise level.

[0041] The smoothness of the energy output data within the influence window can be expressed by the fitting error. If an energy output data is abrupt, it will affect the fitting process of the surrounding energy output data, thereby increasing the fitting error. On the contrary, if the energy output data changes smoothly and steadily, it can be better fitted and the fitting error is smaller.

[0042] An influence window is constructed with the target data as the midpoint and a preset length as the window size. Exemplarily, the window size is set to 15, which can be specifically set by those skilled in the art.

[0043] The energy output data except the target data in the influence window is taken as the influence data; and the influence window is curve fitted using the least square method.

[0044] Calculate the noise level correction value to satisfy the relationship:

[0045] , Indicates energy output data The noise level correction value is Indicates energy output data The noise level, Indicates The fitting value of the data on the curve is affected by Indicates The energy output value that affects the data, Indicates the total number of impact data, represents the hyperbolic tangent function.

[0046] In one embodiment, calculating the noise level further includes: calculating an average energy output value of the energy data set, and normalizing the Euclidean distance between the energy output value of the target data and the average energy output value as the noise level.

[0047] When analyzing the Euclidean distance between the target data in the energy dataset and the average energy output value of the energy dataset, the degree of deviation of the target data from the average level of the entire energy dataset is quantified. This deviation or distance calculation can reveal anomalies or mutation points in the energy dataset.

[0048] In one embodiment, calculating the noise level correction value also includes: synchronously acquiring a power data set according to a preset sampling interval of the energy data set, and taking the power value corresponding to the target data as the target power; calculating the mean of the distance between each power value in the power data set and the target power, and taking the normalized mean as the weight and multiplying the noise level as the noise level correction value.

[0049] S3, obtain a preset number of segmentation points, take any segmentation point as a marking point, use the marking point to recursively segment the energy data set, construct the path length of each energy output data in the segmentation tree after segmentation as a path sequence, and calculate the preference degree of the marking point.

[0050] It should be noted that the traditional RRCF (Robust Random Cut Forest) algorithm randomly selects a value between the maximum and minimum values ​​of a sample set as the split point when constructing a segmentation tree, thereby constructing a segmentation tree. However, this method may lead to inaccurate anomaly detection results due to randomness.

[0051] In one embodiment, a preset number of segmentation points are obtained. For example, quartiles, octaves, sixteenth quartiles, etc. are used as segmentation points.

[0052] Take any segmentation point as a marking point, use the marking point to recursively segment the energy data set, obtain a segmentation result, calculate the preferred degree of the marking point, and the preferred degree satisfies the relationship:

[0053] , Indicates The preference of the split point, Indicates A path sequence of split points, Indicates The corrected value sequence of the split points, Indicates similarity, Represents the adjustment parameter. 0.001 is used to avoid the denominator being 0.

[0054] The function of adjusting the parameter is normalization, and it can also avoid the degree of preference being negative, and the value is generally 1.

[0055] The path length and the abnormality of the energy output data are negatively correlated, that is, the shorter the path length, the more abnormal the energy output data is, while the noise level correction value and the abnormality of the energy output data are positively correlated, that is, the larger the noise level correction value, the more abnormal the energy output data is. Therefore, the lower the similarity between the path sequence and the correction value sequence, the better the segmentation effect.

[0056] S4, traverse all segmentation points, take the segmentation point corresponding to the maximum value of the preference degree as the optimal segmentation point, obtain the final segmentation tree and the abnormal score of each energy output data according to the optimal segmentation point, and take the energy output data with abnormal score greater than the preset threshold as the abnormal point to complete the energy adjustment of the laser therapy device.

[0057] In one embodiment, according to the method of calculating the preference degree in step S3, the preference degrees corresponding to all segmentation points are calculated, and the segmentation point corresponding to the maximum preference degree is taken as the optimal segmentation point.

[0058] The final segmentation tree and the abnormality score of each energy output data are obtained according to the optimal segmentation point, and the energy output data with an abnormality score greater than a preset threshold is regarded as an abnormal point. Exemplarily, the preset threshold is set to 0.64.

[0059] The abnormal points in the energy data set are removed, and the energy data set is supplemented by cubic spline interpolation to obtain the denoised energy data set, thus completing the energy adjustment of the laser therapy device.

[0060] An embodiment of the present invention further discloses a device for adjusting the energy accuracy of a laser therapy device, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for adjusting the energy accuracy of a laser therapy device according to the present invention is implemented.

[0061] The above-mentioned device also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0062] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution device, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0063] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0064] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for adjusting the energy accuracy of a laser therapeutic device, characterized in that: include: Acquire energy output data of the laser therapy device according to a preset sampling interval and construct an energy data set; Taking any energy output data as target data, calculating the noise level of the target data, correcting the noise level to obtain a noise level correction value, traversing the energy data set, and obtaining a correction value sequence; Obtain a preset number of segmentation points, take any segmentation point as a marking point, use the marking point to recursively segment the energy data set, construct the path length of each energy output data in the segmentation tree after segmentation as a path sequence, and calculate the preferred degree of the marking point; Traverse all segmentation points, take the segmentation point corresponding to the maximum value of the preferred degree as the optimal segmentation point, obtain the final segmentation tree and the abnormal score of each energy output data according to the optimal segmentation point, and take the energy output data with abnormal score greater than the preset threshold as the abnormal point to complete the energy adjustment of the laser therapy device; Among them, the degree of preference satisfies the relationship: , Indicates The preference of the split point, Indicates A path sequence of split points, Indicates The corrected value sequence of the split points, Indicates similarity, Indicates the adjustment parameter.

2. The method for adjusting the energy accuracy of a laser therapeutic device according to claim 1, characterized in that: Calculating the noise level includes: A coordinate system is constructed with the sampling time as the horizontal axis and the value of the energy output data as the vertical axis, and two energy output data adjacent to the target data are recorded as the left reference point and the right reference point in the order of the sampling time, and a first straight line passing through the left reference point and the target data, a second straight line passing through the right reference point and the target data, and a third straight line passing through the target data and perpendicular to the horizontal axis are obtained respectively; The angle between the first straight line and the third straight line is taken as the first angle, the angle between the second straight line and the third straight line is taken as the second angle, and the first angle and the second angle are less than or equal to a right angle; The angle sum of the first angle and the second angle is calculated, and the sine value of the difference between the angle sum and the straight angle is used as the noise degree.

3. The method for adjusting the energy accuracy of a laser therapeutic device according to claim 2, characterized in that: When the target data is located at the beginning or end of the energy data set, the noise level is 0.

4. The method for adjusting the energy accuracy of a laser therapeutic apparatus according to claim 1, characterized in that: Calculating the noise level further includes: The average energy output value of the energy data set is calculated, and the Euclidean distance between the energy output value of the target data and the average energy output value is normalized as the noise degree.

5. The method for adjusting the energy accuracy of a laser therapeutic apparatus according to claim 1, characterized in that: Calculating the noise level correction value includes: An influence window is constructed with the target data as the midpoint and the preset length as the window size, and the energy output data except the target data in the influence window is used as the influence data; The least square method is used to perform curve fitting on the impact window; The noise level correction value satisfies the relationship: , Indicates energy output data The noise level correction value is Indicates energy output data The noise level, Indicates The fitting value of the data on the curve is affected by Indicates The energy output value that affects the data, Indicates the total number of impact data, represents the hyperbolic tangent function.

6. The method for adjusting the energy accuracy of a laser therapeutic apparatus according to claim 1, characterized in that: Calculating the noise level correction value also includes: Synchronously acquiring a power data set according to a preset sampling interval of the energy data set, and taking a power value corresponding to the target data as the target power; The average of the distances between each power value in the power data set and the target power is calculated, the normalized average is used as a weight, and the result of multiplying the weight by the noise level is used as a noise level correction value.

7. The method for adjusting the energy accuracy of a laser therapeutic apparatus according to claim 1, characterized in that: The abnormal points are removed, and the energy data set is supplemented by cubic spline interpolation to obtain the denoised energy data set, thus completing the energy adjustment of the laser therapy device.

8. A laser therapy device energy precision adjustment device, characterized in that: include: Processor; and A memory storing computer instructions, wherein when the computer instructions are executed by a processor, the device executes the method for adjusting the energy accuracy of a laser therapy device according to any one of claims 1 to 7.

Images