Multi-wavelength adaptive adjustment method for infrared light prostate therapeutic apparatus

Abstract

The embodiment of the invention provides a multi-wavelength adaptive adjustment method for an infrared light prostate therapeutic apparatus, and relates to the technical field of wavelength adaptive adjustment technologies. The method comprises the following steps: acquiring reflected light information of reflected light of a first wavelength light beam of a target light source and temperature information of a target object; performing multi-modal analysis processing on the temperature information, the energy information and the spectral information to obtain a first analysis result; and carrying out wavelength adjustment operation on the target light source according to the first analysis result so as to emit a light beam with a second wavelength to the target object. According to the invention, the problem that the wavelength cannot be adaptively adjusted is solved, and the effect of improving the adaptability of equipment is further achieved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of infrared light wavelength adjustment, and more specifically, to a multi-wavelength adaptive adjustment method for an infrared light prostate treatment instrument. Background Art

[0002] The technology of using light of different wavelengths to illuminate some things so that they can grow or change to different degrees according to needs has been widely applied in many fields.

[0003] For example, invention patent applications such as the application number CN202410600957.3 with the patent application name of an optical positioning navigation system and method in precise laser surgery for prostate hyperplasia, and the application number CN202420378968.7 with the patent application name of a treatment tool for a laser treatment device and a laser treatment device, etc. are all applications in the field of prostate treatment; they can all emit lasers of different wavelengths under different circumstances to achieve functions such as navigation positioning.

[0004] However, there are some limitations in the existing devices in terms of wavelength control. For example, some devices may only use a light source of a single wavelength and cannot be adjusted flexibly, which greatly affects the use. Summary of the Invention

[0005] The embodiments of the present invention provide a multi-wavelength adaptive adjustment method for an infrared light prostate treatment instrument to at least solve the problem that the wavelength cannot be adaptively adjusted in the related art.

[0006] According to an embodiment of the present invention, there is provided a multi-wavelength adaptive adjustment method for an infrared light prostate treatment instrument, including: Obtaining the reflected light information of the reflected light of the first wavelength beam of the target light source and the temperature information of the target object, where the reflected light is obtained after the target object absorbs and reflects the first wavelength beam, and the reflected light information includes the energy information and spectral information of the reflected light; Performing multi-modal analysis processing on the temperature information, energy information, and spectral information to obtain a first analysis result; Performing a wavelength adjustment operation on the target light source according to the first analysis result to emit a beam of the second wavelength to the target object.

[0007] In an exemplary embodiment, the performing multi-modal analysis processing on the temperature information, energy information, and spectral information includes: Performing preprocessing on the temperature information, energy information, and spectral information; Performing feature extraction processing on the preprocessing result to obtain information features; Determine a first region of the target object according to the information feature, and determine the region information of the first region; Construct the information feature into a feature tensor; Based on the region information, determine the dynamic weight of the feature tensor through a preset attention mechanism; Based on the feature tensor, region information, and the dynamic weight, determine the region state of the first region of the target object, and use the region state as the first analysis result.

[0008] In an exemplary embodiment, the preprocessing of the temperature information, energy information, and spectral information includes: Perform data cleaning processing on the temperature information, energy information, and spectral information; Perform normalization processing on the data cleaning processing result, and use the normalization processing result as the preprocessing result.

[0009] In an exemplary embodiment, the data cleaning processing of the temperature information includes: Perform filtering processing on the temperature information using moving average filtering or Gaussian filtering; Perform stage classification on the filtering processing result through a preset temperature threshold, and use the stage classification result as the temperature information data cleaning processing result.

[0010] In an exemplary embodiment, the data cleaning processing of the spectral information includes: Perform high-frequency noise cleaning on the spectral information using wavelet transform; Perform response difference elimination processing on the high-frequency noise cleaning result through multiplicative scatter correction, and use the response difference elimination processing as the spectral information data cleaning processing result.

[0011] In an exemplary embodiment, after performing feature extraction processing on the preprocessing result to obtain information features, the method further includes: Determine the spatial constraint information of the first region according to the temperature distribution feature and spectral space feature included in the information feature, where the region information includes the spatial constraint information.

[0012] In an exemplary embodiment, after performing feature extraction processing on the preprocessing result to obtain information features, the method further includes: Determine predicted temperature information according to the spectral energy distribution feature included in the information feature; Match the predicted temperature information with the obtained temperature information, and if the match is unsuccessful, determine that the information feature is abnormal.

[0013] In an exemplary embodiment, the operation of adjusting the wavelength of the target light source according to the first analysis result includes: Determining the wavelength range and energy amplitude of the second wavelength according to the first analysis result; Performing a wavelength adjustment action based on the wavelength range and the energy amplitude.

[0014] In an exemplary embodiment, after performing feature extraction processing on the preprocessing result to obtain information features, the method further includes: Constructing the information features into an information feature matrix; Calculating the probability value of the image composed of pixel points corresponding to the information feature matrix through a preset attention mechanism function; When the probability value is within a preset range, determining that the information features meet the requirements, otherwise determining it as abnormal.

[0015] According to another embodiment of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, and wherein the computer program is configured to execute the steps in the above method embodiments when running.

[0016] According to another embodiment of the present invention, there is also provided an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in the above method embodiments.

[0017] Through the present invention, by real-time monitoring the temperature, reflected light energy, and spectral information of tissues, performing multimodal data analysis, and dynamically adjusting the wavelength and power of the light source according to the analysis results, the problem of non-self-adaptive wavelength adjustment can be solved, and the effect of improving the self-adaptability of the device can be achieved. Description of the Drawings

[0018] Figure 1 is a flowchart of a multi-wavelength adaptive adjustment method for an infrared light prostate treatment device according to an embodiment of the present invention; Figure 2 is a structural block diagram of a multi-wavelength adaptive adjustment device for an infrared light prostate treatment device according to an embodiment of the present invention. Detailed Embodiments

[0019] Next, the technical solutions in the embodiments of the present application will be described in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0020] Hereinafter, terms such as "first", "second", etc. are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", etc. may explicitly or implicitly include one or more of such features. In the description of this application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0021] In addition, in this application, orientation terms such as "upper", "lower", "left", "right", etc. may include but are not limited to being defined relative to the schematic placement of components in the drawings. It should be understood that these directional terms may be relative concepts, which are used for relative description and clarification and may change accordingly with the change in the orientation of the components placed in the drawings.

[0022] In this application, unless otherwise clearly specified and defined, the term "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or integrated; it can be directly connected or indirectly connected through an intermediate medium. In addition, the term "coupling" can be a way of achieving electrical connection for signal transmission.

[0023] As used herein, "about", "substantially" or "approximately" includes the stated value and the average value within an acceptable deviation range of the specific value, where the acceptable deviation range is determined by a person of ordinary skill in the art considering the measurement being discussed and the errors associated with the measurement of the specific quantity (i.e., the limitations of the measurement system).

[0024] The technology of using light of different wavelengths to illuminate some things so that they can grow or change to different extents according to requirements has been widely applied in many fields. For example, according to the growth characteristics of different plants, light beams of different wavelengths are used for illumination to cause specific growth of local tissues of the plants, or according to the different characteristics of minerals, they are illuminated to cause specific exfoliation or structural changes in different positions of the minerals, etc. It can also be, such as the invention patent application with the application number CN202410600957.3 and the patent application name of the optical positioning navigation system and method in precision laser surgery for benign prostatic hyperplasia, the device with the application number CN202420378968.7 and the patent application name of the treatment tool for a laser treatment device and the laser treatment device, etc., which are all applied in the field of prostate treatment; they can all emit laser light of different wavelengths under different circumstances, so as to achieve functions such as navigation and positioning; to achieve these functions and to adapt to various usage environments, the laser generating device needs to have a certain wavelength adjustment ability, so that it can emit laser light of different wavelengths under different circumstances, and this adjustment is generally achieved by adjusting its emission power, etc.; and in order to adjust the sight wavelength more precisely and reduce the content of manual operation, it is necessary to make these devices be able to automatically adaptively adjust the wavelength according to the changes in the environment and the object of action.

[0025] To this end, in this embodiment, a multi - wavelength adaptive adjustment method for an infrared light prostate treatment device is provided. This device can adaptively adjust the wavelength according to the actual changes of different action targets; it should be particularly noted that the adaptive adjustment method of its wavelength can also be applied to multiple fields such as plant growth management and mineral trimming, and is not limited to the treatment device. Therefore, if the application field changes, but as long as the multi - wavelength adaptive adjustment method in this application is adopted, it will fall within the scope of this application.

[0026] Embodiment 1

[0027] Specifically, Figure 1 is a flowchart of a multi - wavelength adaptive adjustment method for an infrared light prostate treatment device according to an embodiment of the present invention. As Figure 1 shown, this process includes the following steps: Step S11, obtain the reflected light information of the reflected light of the first - wavelength light beam of the target light source and the temperature information of the target object. Among them, the reflected light is obtained after the target object absorbs and reflects the first - wavelength light beam, and the reflected light information includes the energy information and spectral information of the reflected light; In this embodiment, after irradiating the target object, the target object will partially absorb the light beam. During the absorption process, as energy accumulates, the temperature of the target object itself and the surrounding environment will change. At the same time, part of the light beam will also be reflected. Since different target objects have different absorption and reflection capabilities for the light beam, the correlation between the target object and the light beam can be judged by observing the reflected light and the changes in the states such as the temperature of the surrounding environment or the target object itself.

[0028] For example, if it is applied in the field of light therapy instruments, infrared light with a wavelength of 660nm - 1500nm is emitted to promote some changes in tissues such as the prostate. For example, hemoglobin in prostate tissue has a high absorption rate for 660nm red light; near-infrared light of 800 - 900nm can penetrate deep into tissues and is absorbed by water molecules and lipids in the tissues, generating a mild thermal effect; light of 980nm is strongly absorbed by water molecules and can effectively promote the water metabolism of prostate tissue; 1064nm near-infrared light has strong tissue penetration ability and is absorbed by melanin and hemoglobin in the tissues; mid-infrared light of 1400 - 1500nm can be absorbed by proteins and collagen in the tissues; and so on.

[0029] It should be noted that the first-wavelength light beam includes the light beam before adjustment, and its wavelength can be a specific value, a range value, or multiple values; the target object can be animals and plants, minerals, or other things that can absorb and reflect light beams (such as prostate tissue); the collection of reflected light can be achieved through devices or apparatuses such as optical sensors, fiber optic probes, or a combination of fiber optic probes and mirrors; temperature information can be collected through temperature-sensing devices or apparatuses such as temperature sensors; in addition to the energy and spectral information of the reflected light, the reflected light information can also include the time when the reflected light is received, the change and duration of the light intensity of the reflected light and the corresponding time points, the distribution of the reflected light on the receiving device, etc. (for example, arranging multiple fiber optic probes in a certain array, and then determining the distribution of the reflected light according to the reflected light reception situation at each array point; the distribution situation includes energy distribution, intensity distribution, duration distribution, etc., which are not limited here); the energy information includes the energy value of the reflected light, and the spectral information includes spectral distribution, spectral characteristics, etc.

[0030] For example, when applied to a light therapy device, the light therapy device irradiates the prostate area with a beam of an initial wavelength of 800 nm. At the same time, through an optical fiber probe array, the light beam information reflected by the prostate tissue is collected, and this information includes the energy value and spectral distribution of the reflected light. At the same time, temperature sensors distributed around the prostate continuously monitor the change of tissue temperature. For example, the energy information of the reflected light shows the degree of light absorption by the tissue, while the spectral information reveals the distribution of different components (such as hemoglobin, water molecules, etc.) in the tissue.

[0031] Step S12: Perform multimodal analysis and processing on the temperature information, energy information, and spectral information to obtain a first analysis result. In this embodiment, by analyzing temperature, energy, and spectrum, etc., the current state of the target object is determined, and then the wavelength is adjusted according to its state, so as to achieve adaptive adjustment of the wavelength.

[0032] Specifically, it includes: Step S121: Perform preprocessing on the temperature information, energy information, and spectral information. Among them, the preprocessing includes: Step S1211: Perform data cleaning processing on the temperature information, energy information, and spectral information.

[0033] Step S1212: Perform normalization processing on the data cleaning processing result, and use the normalization processing result as the preprocessing result.

[0034] In this embodiment, cleaning the data is to remove interference information and ensure the accuracy of subsequent data processing, while normalization is to unify the formats of various types of data to facilitate subsequent unified processing of the data.

[0035] Among them, the data cleaning processing for temperature information can be to perform filtering processing on the temperature information by using moving average filtering or Gaussian filtering, and then perform stage classification on the filtering processing result through a preset temperature threshold, and use the stage classification result as one of the data cleaning processing results of the temperature information. Here, by calculating the average value of the data within the window, the temperature curve can be effectively smoothed, the influence of short-term fluctuations and random noise can be reduced, and this method is simple and easy to implement, which is beneficial to reducing the development cost. And using the Gaussian function to perform weighted average on the data can better retain the trend of temperature change, while removing high-frequency noise and maintaining the edge features of the data. Performing stage classification is to establish a mapping relationship between different wavelengths, different irradiation durations and the state of the target object according to the classification structure subsequently, so as to improve the accuracy of adaptive adjustment.

[0036] Since spectral data usually contains high-frequency noise, which may originate from the electronic noise of the instrument, environmental interference, or the inhomogeneity of the sample, wavelet transform is used here to clean the high-frequency noise of the spectral information, so as to remove the noise while retaining the main features of the spectral signal. At the same time, due to differences in the physical properties of the sample (such as particle size, surface roughness, etc.) or the measurement conditions of the instrument, etc., response differences will be generated in the spectral data. To eliminate this difference, the response difference can be eliminated by applying multiplicative scatter correction to the result of high-frequency noise cleaning. Then, the response difference elimination process is used as one of the results of the spectral information data cleaning process.

[0037] Exemplarily, a moving average filter is used to smooth the temperature data to reduce the influence of short-term fluctuations and random noise. For example, when applied to a light therapy instrument, if the temperature sensor connected to the light therapy instrument detects that the temperature in a certain area of the prostate rises sharply in a short period of time, this may be due to local overheating caused by the photothermal effect. Through filtering, the trend of temperature change can be observed more clearly. And wavelet transform is used to denoise the spectral data to remove high-frequency noise. For example, if there is interference caused by instrument electronic noise in the spectral data, wavelet transform can help retain the main features of the spectral signal (such as the absorption peak of hemoglobin). Similarly, if applied in the fields of plant searchlight and mineral exploration, similar methods can be used for processing.

[0038] Step S122, perform feature extraction processing on the preprocessing result to obtain information features; In this embodiment, when performing feature extraction, a shared feature space of temperature-energy-spectra can be constructed first, and a graph convolutional network (GCN) can be used to extract cross-modal correlation features. For example, the correlation between the temperature gradient and the near-infrared spectral reflectance can reflect the metabolically active regions in plants, or regions suspected of being abnormal, etc. It should be noted that the network model for feature extraction can be other models besides GCN, and it is not limited here.

[0039] Among them, the information features include the temperature change rate, temperature gradient, temperature peak value, peak value of reflected light energy, energy distribution, energy change rate, spectral absorption / reflection peak, spectral width, spectral intensity, etc. When performing feature extraction, the extracted features can be dimensionally reduced to remove redundant features and retain the most representative features, or features most relevant to the state and characteristics of the target object can be selected for feature extraction. Additionally, after obtaining the relevant information features, the relevant information features are arranged in a certain order to form a feature vector for convenient subsequent processing. For example, feature values such as the temperature change rate, energy peak value, and spectral absorption peak are combined into a high-dimensional feature vector, or a feature matrix is formed, etc., which is not limited herein. For example, when applied to a light therapy instrument, the light therapy instrument can determine the response speed of prostate tissue to photothermal energy based on the temperature change rate, the temperature gradient can indicate the internal heat distribution of the tissue, and the hemoglobin absorption peak can be used to evaluate the blood flow of the tissue.

[0040] Step S123: Determine a first region of the target object according to the information features, and determine the region information of the first region. In this embodiment, the first region mainly includes regions in the target object where abnormalities may exist or changes are relatively obvious. For example, for regions in plants where tissue changes are abnormal or obvious, or regions in minerals where crystal structure changes are abnormal, etc.

[0041] Specifically, regions with a relatively fast temperature change, or regions with a relatively large or small temperature average value can be determined according to the temperature change. An energy abnormal region can also be determined according to the average value and standard deviation of the reflected light energy, or a distribution region of a specific component can be identified according to the absorption peak in the spectrum, etc. The first region is a region with specific temperature, energy, or spectral characteristics. Subsequently, a corresponding feature tensor can be constructed according to the regional characteristics (such as area, shape, etc.) of this region, or it can be used for other processing.

[0042] Exemplarily, when applied to a light therapy instrument, the light therapy instrument can identify regions in the prostate tissue where abnormalities may exist according to the extracted features. For example, if the temperature change rate in a certain region is significantly higher than that in the surrounding regions, this may indicate that there is inflammation or poor blood flow in this region. At this time, the prostate tissue is divided into different functional regions, such as an inflammation region, a region with rich blood flow, and a normal tissue region, and then the spectral characteristics of these regions are compared. For example, the inflammation region may exhibit a higher temperature and specific spectral characteristics.

[0043] Step S124: Construct the information features into a feature tensor. In this embodiment, constructing the relevant information into a feature tensor is to facilitate the association of the spatio-temporal changes of the target object with its information features, so that the areas that need to be concerned can be determined in subsequent processing, and relevant change strategies can be selected in a timely manner according to the changes in specific areas, thereby improving the efficiency and accuracy of adaptive adjustment.

[0044] Specifically, a multi-dimensional feature tensor of space-time and feature channels can be constructed according to the distribution of features. For example: (Formula 1) In the formula, is the multi-dimensional feature tensor, is the spatial dimension of the first area, where H is the length (height) of the first area, W is the width of the first area, and C is the modal feature channels of temperature, energy, and spectral band.

[0045] Step S125, based on the area information, determine the dynamic weight of the feature tensor through a preset attention mechanism; In this embodiment, through the attention mechanism, the dynamic weight distribution of the feature tensor can be realized, and at the same time, the spatial position and multi-modal can be associated, which can improve the recognition accuracy, and the weight is adjusted in real time with the input data, which can optimize the synergistic effect of multi-wavelength or multi-modal. Specifically: (Formula 2) In the formula, is the normalized dynamic weight, which can reflect the dynamic importance of different areas. Q is the query vector of the target object (such as the state type of the target object, the area features that need to be concerned currently, the attention attributes of the area (such as temperature gradient, spectral reflectance), the linear projection of the original features, etc.), is the feature vector, d is the dimension, is to prevent the product result from being too large and causing gradient disappearance; Softmax( ) is the attention function, which is used to convert the scores into a probability distribution, ensure that the sum of the weights is 1, and highlight the key areas.

[0046] It should be noted that in Formula 2, the area information needs to be encoded into a learnable embedding vector first to enhance the model's perception ability of the area distribution. Then, the relevance between areas is measured by the product of Q and K, so that areas with high correlation (such as high-temperature areas and near-infrared absorption areas) can obtain greater weights, and then normalized through Softmax(), so that the weights change adaptively with the input data, providing a data basis for the subsequent adaptive adjustment of wavelengths.

[0047] For example, when applied to a light therapy instrument, the light therapy instrument can assign higher weights to certain areas, or when applied to the field of plant searchlights, areas with higher plant absorption peaks may be assigned higher weights, which can be specifically adjusted according to the actual application scenario and are not limited here.

[0048] Step S126, based on the feature tensor, region information, and the dynamic weight, determine the region state of the first region of the target object, and use the region state as the first analysis result.

[0049] In this embodiment, after determining the feature tensor, region information such as the area / shape of the first region, and the dynamic weight, the state of the first region of the target object is judged, and then the wavelength is adaptively adjusted.

[0050] For example, if the temperature of a certain area rises abnormally, and the spectral characteristics show that this area has strong absorption of infrared light at the current wavelength, at this time, this area is determined as the first region, and its temperature distribution, energy distribution, and spectral characteristics are extracted. Then, the weights of each feature are determined through the attention mechanism, and the region state is comprehensively analyzed. If the region state indicates that the temperature of this area is too high, it may be necessary to adjust the wavelength of the light source and switch to a wavelength with weaker absorption to reduce the temperature of this area, and so on.

[0051] Exemplarily, when applied to a light therapy instrument, the light therapy instrument can comprehensively consider the feature tensor, region information, and dynamic weight to determine the region state of a certain tissue. For example, if the temperature of a certain area rises abnormally, and the spectral characteristics show that this area has strong absorption of infrared light at the current wavelength, this may indicate that there is a risk of overheating in this area, and the wavelength needs to be adjusted to reduce the temperature.

[0052] Specifically, the region state Z can be calculated by the following formula: (Formula 3) In the formula, n is the number of sub-regions in the first region.

[0053] Step S13, perform a wavelength adjustment operation on the target light source according to the first analysis result to emit a beam of the second wavelength to the target object.

[0054] In this embodiment, by controlling the wavelength adjustment device of the light source, such as a tunable laser or a filter, etc., the wavelength of the light source is adjusted from the first wavelength to the second wavelength, or the power of the light source can also be adjusted to change from the first wavelength to the second wavelength, which is not limited here.

[0055] It should be noted that, in order to adjust the wavelength more precisely, it is necessary to establish the correlation between the regional state and the wavelength, so that the wavelength can be adjusted to the predetermined wavelength after the region reaches a certain state; for example, when the regional state value is A, switch to the infrared light with the wavelength of B and the energy of C to reduce the absorption efficiency of the target object, and so on.

[0056] Among them, the operation of adjusting the wavelength of the target light source according to the first analysis result includes: Step S131, determining the wavelength range and energy amplitude of the second wavelength according to the first analysis result; Step S132, performing a wavelength adjustment action based on the wavelength range and the energy amplitude.

[0057] In this embodiment, according to the pre-established correlation between the wavelength and the state, the wavelength range, energy, etc. corresponding to the regional state are determined, and then the device is controlled to switch the lens / crystal / power, so that the subsequent emitted light beam has the corresponding wavelength range and energy.

[0058] For example, assume that the control software interface of the therapeutic instrument is as shown in Table 1 below: Table 1

[0059] In the control software, adjust the wavelength adjustment option from 1064 nm to 1400 nm, and at the same time reduce the energy amplitude from 10 W / cm² to 5 W / cm². Then the system automatically adjusts the cavity length of the laser or the angle of the external cavity filter to make the output wavelength become 1400 nm, and adjusts the pump current of the laser or the output power of the fiber coupler to reduce the energy amplitude to 5 W / cm²; subsequently, continuously collect the reflected light information and the temperature information of the target object. If the first analysis result changes, the wavelength adjustment also changes accordingly, that is, the wavelength adjustment operation is repeated, and the wavelength adjustment operation is adjusted in real time according to the changes of the reflected light information and the temperature information of the target object.

[0060] Through the above steps, since the temperature, reflected light energy and spectral information of the tissue are monitored in real time, multi-modal data analysis is carried out, and the wavelength and power of the light source are dynamically adjusted according to the analysis result, the problem that the wavelength cannot be adaptively adjusted is solved, and the adaptability of the device is improved.

[0061] Embodiment 2

[0062] The difference from Embodiment 1 is that, after performing feature extraction processing on the preprocessing result to obtain information features, the method further includes: Step S1221: Determine the spatial constraint information of the first region according to the temperature distribution feature and spectral spatial feature included in the information feature, where the region information includes the spatial constraint information.

[0063] In this embodiment, when calculating the regional state Z, to further ensure the calculation accuracy, the constraint relationship between the temperature distribution feature and the spectral spatial feature can also be introduced. Specifically: (Formula 4) In the formula, is the correlation of the temperature distribution feature or spectral spatial feature, is the balancing coefficient of the constraint, and n is the number of sub-regions in the first region.

[0064] Embodiment 3

[0065] The difference from Embodiment 1 is that to further ensure the accuracy of the data, after performing feature extraction processing on the preprocessing result to obtain the information feature, the method further includes: Step S1222: Determine the predicted temperature information according to the spectral energy distribution feature included in the information feature; Step S1223: Match the predicted temperature information with the obtained temperature information. If the match is unsuccessful, determine that the information feature is abnormal.

[0066] In this embodiment, since within a certain wavelength range, the temperature of the target object and the spectral energy distribution of the reflected light are in a functional relationship, the temperature situation can be predicted through the detected spectral energy distribution feature, and then this temperature is matched with the actually detected temperature, thereby determining whether the detected data is correct.

[0067] For example, through spectral analysis, the reflected light energy at a certain wavelength is obtained. According to the known relationship model between spectral energy and temperature: (Formula 5) Then substitute the actual data to obtain a predicted temperature of 32.5, while the actually detected temperature is 35. At this time, the temperature difference is 2.5, which is greater than the range difference. Thus, it is determined that the data may be abnormal, and so on.

[0068] Embodiment 4

[0069] The difference from Embodiment 3 is that to further ensure the accuracy of the data, after performing feature extraction processing on the preprocessing result to obtain the information feature, the method further includes: Step S1224: Construct the information feature into an information feature matrix; Step S1225, calculate the probability value of the image composed of the pixel points corresponding to the information feature matrix through a preset attention mechanism function; Step S1226, when the probability value is within a preset range, determine that the information feature meets the requirements, otherwise determine it as abnormal.

[0070] In this embodiment, after arranging multiple optical fiber probes in a certain array to obtain a receiving array, the information features corresponding to the receiving array are constructed into an information feature matrix. Subsequently, the feature values in the normalized matrix are used as gray values. At this time, the information feature matrix can be regarded as a gray pixel map. Then, this gray pixel map is input into the attention model, and the confidence value is calculated through its Softmax function. When the confidence value is within the preset range, it is determined that the information feature meets the requirements, otherwise it is determined as abnormal, and so on.

[0071] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases, the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc), and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0072] In this embodiment, a multi-wavelength adaptive adjustment device for an infrared light prostate treatment instrument is also provided. This device is used to implement the above embodiments and preferred implementation methods, and those that have been described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0073] Figure 2 is a structural block diagram of a multi-wavelength adaptive adjustment device for an infrared light prostate treatment instrument according to an embodiment of the present invention. As Figure 2 shown, the device includes: An information acquisition module 21, configured to acquire the reflected light information of the reflected light of the first wavelength beam of the target light source and the temperature information of the target object. Wherein, the reflected light is obtained after the target object absorbs and reflects the first wavelength beam, and the reflected light information includes the energy information and spectral information of the reflected light; The multimodal analysis module 22 is configured to perform multimodal analysis processing on the temperature information, energy information, and spectral information to obtain a first analysis result; The wavelength adjustment module 23 is configured to perform a wavelength adjustment operation on the target light source according to the first analysis result to emit a light beam with a second wavelength to the target object.

[0074] It should be noted that the above-mentioned modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited thereto: the above-mentioned modules are all located in the same processor; or, the above-mentioned modules are respectively located in different processors in any combination form.

[0075] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, and the computer program is configured to execute the steps in the above method embodiment when running.

[0076] In an exemplary embodiment, the above computer-readable storage medium may include, but is not limited to: USB flash drive, read-only memory (ROM for short), random access memory (RAM for short), mobile hard disk, magnetic disk, or optical disc and other various media that can store computer programs.

[0077] An embodiment of the present invention further provides an electronic device, including a memory and a processor, a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in the above method embodiment.

[0078] In an exemplary embodiment, the above electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the above processor, and the input / output device is connected to the above processor.

[0079] Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and brevity of description, only the above division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0080] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.

[0081] The units described as separate components may or may not be physically separated. The components displayed as units may be one physical unit or multiple physical units, that is, they can be located in one place, or they can be distributed to multiple different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] In addition, in each embodiment of the present application, each functional unit can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0083] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions for causing a device (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical discs and other various media that can store program codes.

[0084] The above content is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A multi-wavelength adaptive adjustment method for an infrared light prostate therapeutic device, characterized in that: include: Acquire reflected light information of reflected light of a first wavelength light beam of a target light source and temperature information of a target object, wherein the reflected light is obtained after the target object absorbs and reflects the first wavelength light beam after receiving the first wavelength light beam, and the reflected light information includes energy information and spectrum information of the reflected light; Performing multimodal analysis on the temperature information, energy information, and spectrum information to obtain a first analysis result; A wavelength adjustment operation is performed on the target light source according to the first analysis result to emit a light beam with a second wavelength to the target object.

2. The method according to claim 1, characterized in that The multimodal analysis and processing of the temperature information, energy information and spectrum information includes: Preprocessing the temperature information, energy information and spectrum information; Perform feature extraction processing on the preprocessing results to obtain information features; Determine a first area of ​​the target object according to the information feature, and determine area information of the first area; constructing the information features into a feature tensor; Based on the region information, determining the dynamic weight of the feature tensor through a preset attention mechanism; A region state of a first region of the target object is determined based on the feature tensor, the region information, and the dynamic weight, and the region state is used as the first analysis result.

3. The method according to claim 2, characterized in that The preprocessing of the temperature information, energy information and spectrum information comprises: Performing data cleaning processing on the temperature information, energy information and spectrum information; The data cleaning result is normalized and the normalized result is used as the preprocessing result.

4. The method according to claim 3, characterized in that The data cleaning process for the temperature information includes: The temperature information is filtered using a sliding average filter or a Gaussian filter; The filtering processing results are classified into stages according to a preset temperature threshold, and the stage classification results are used as the temperature information data cleaning processing results.

5. The method according to claim 3, characterized in that: The data cleaning process for the spectral information includes: Using wavelet transform to clean the spectral information from high-frequency noise; The high-frequency noise cleaning result is subjected to response difference elimination processing through multivariate scattering correction, and the response difference elimination processing is used as the spectral information data cleaning processing result.

6. The method according to claim 2, characterized in that After performing feature extraction processing on the preprocessing result to obtain information features, the method further includes: The spatial constraint information of the first region is determined according to the temperature distribution characteristics and the spectral space characteristics included in the information characteristics, wherein the region information includes the spatial constraint information.

7. The method according to claim 2, characterized in that: After performing feature extraction processing on the preprocessing result to obtain information features, the method further includes: Determining predicted temperature information according to the spectral energy distribution characteristics contained in the information characteristics; The predicted temperature information is matched with the acquired temperature information, and when the match is unsuccessful, it is determined that an abnormality exists in the information feature.

8. The method according to claim 1, characterized in that The wavelength adjustment operation of the target light source according to the first analysis result includes: Determine the wavelength range and energy amplitude of the second wavelength according to the first analysis result; Based on the wavelength range and the energy amplitude, a wavelength adjustment action is performed.

9. The method according to claim 2, characterized in that: After performing feature extraction processing on the preprocessing result to obtain information features, the method further includes: constructing the information features into an information feature matrix; Calculate the probability value of the image composed of pixels corresponding to the information feature matrix through a preset attention mechanism function; When the probability value is within a preset range, it is determined that the information feature meets the requirements, otherwise it is determined to be abnormal.

Images