Laser power determination model construction method, and laser power automatic adjustment method

Abstract

The present application relates to the field of endoscopic imaging, and discloses a laser power determination model construction method, and a laser power automatic adjustment method. The laser power determination model construction method comprises: performing data fitting on the basis of an air environment image data set, a solution environment image data set, a laser power set, and a preset curve fitting method, so as to obtain a laser power determination model. Also disclosed is a laser power automatic adjustment method, implemented by means of the laser power determination model.

Description

Laser power determination model construction method and laser power automatic adjustment method

[0001] This application claims priority to Chinese Patent Application No. 202410852246.5, filed on June 28, 2024, entitled "Laser power determination model construction method, adjustment method and storage medium", and Chinese Patent Application No. 202410852114.2, filed on June 28, 2024, entitled "Confocal endoscope laser power automatic adjustment method", the entire contents of which are incorporated herein by reference. The disclosure of all related applications that are cited herein and that are in the possession of the applicant(s) are hereby incorporated by reference in their entirety. TECHNICAL FIELD

[0002] The present application relates to the field of endoscopic imaging, and more particularly, to a laser power determination model construction method and a laser power automatic adjustment method. BACKGROUND

[0003] A confocal endoscope is a medical device that can be inserted into the human body through a channel such as a gastroscope or a colonoscope to obtain a local histological image to achieve precise diagnosis of micro lesions, gastrointestinal lesions and early gastrointestinal cancer. The basic principle of the confocal endoscope is to illuminate the tissue with a laser and then detect the fluorescence reflected from the tissue. Under the condition that the concentration of the fluorescent dye is constant, different laser powers will result in images of different qualities. Too high or too low laser power will result in over-bright or over-dark images, which will make it impossible to distinguish details in the resulting images and lack sufficient contrast, i.e., reduce the image quality. Therefore, appropriate laser power is crucial to the imaging quality.

[0004] When a confocal endoscope is applied to clinical examination, the same dose of fluorescent dye is given to the examinee, but due to individual differences, the concentration of the fluorescent dye in the tissue will be different. In order to obtain a good quality image, it is usually necessary to adjust the laser power to an appropriate level. If the physician manually adjusts the laser power, it will increase the operation complexity and workload, and the physician needs to be trained in advance to be able to reasonably adjust the laser power according to the image at that time, which is not an easy task. Therefore, how to simplify the laser power adjustment of the confocal endoscope has become a problem to be solved. SUMMARY

[0005] A series of simplified concepts are introduced in the summary section, which will be further described in detail in the detailed description section. The summary section of the present application does not mean to attempt to limit the key features and essential technical features of the claimed technical solutions, nor does it mean to determine the protection scope of the claimed technical solutions.

[0006] In a first aspect, the application provides a laser power determination model construction method, the method comprising:

[0007] selecting K different laser powers to construct a laser power set;

[0008] respectively acquiring N frames of image data of the endoscope probe in air at each laser power to construct an air environment image data set;

[0009] respectively acquiring N frames of image data of the endoscope probe immersed in a reference concentration of sodium fluorescein solution at each laser power to construct a solution environment image data set;

[0010] performing data fitting based on the air environment image data set, the solution environment image data set, the laser power set, and a preset curve fitting method to obtain the laser power determination model, wherein the laser power determination model comprises a first correspondence relationship and a second correspondence relationship, the first correspondence relationship is a correspondence relationship between air environment image data and the K different laser powers, and the second correspondence relationship is a correspondence relationship between solution environment image data and the K different laser powers.

[0011] In a feasible implementation, the data fitting based on the air environment image data set, the solution environment image data set, the laser power set, and the preset curve fitting method to obtain the laser power determination model comprises:

[0012] constructing an air core brightness signal average value set based on the average value of the brightness signal values of all core positions at each laser power in the air environment image data set ;

[0013] constructing a solution core brightness signal average value set based on the average value of the brightness signal values of all core positions at each laser power in the solution environment image data set ;

[0014] performing data fitting according to the air core brightness signal average value set, the laser power set, and the preset curve fitting method to construct the first correspondence relationship;

[0015] performing data fitting according to the solution core brightness signal average value set, the laser power set, and the preset curve fitting method to construct the second correspondence relationship;

[0016] creating the laser power determination model according to the first correspondence relationship and the second correspondence relationship.

[0017] In a feasible implementation, the method further comprises:

[0018] Positioning the fiber core using the air environment image data set or the solution environment image data set to obtain a fiber core position.

[0019] In an embodiment, the method for obtaining the average value of the brightness signal value of the fiber core position and the average value of the fiber core brightness signal in the solution is specifically:

[0020] In the air environment image data set and the solution environment image data set, respectively, the N frames of image data collected at each laser power are averaged by pixels to obtain an average image set in the air and an average image set in the solution .

[0021] The average set of fiber core brightness signal values in the air is extracted at the fiber core position on the average image set in the air.

[0022] The average set of fiber core brightness signal values in the solution is extracted at the fiber core position on the average image set in the solution.

[0023] In an embodiment, the reference concentration is the average value of the fiber core brightness signal in the reference solution corresponding to the preset interval of the brightness value, the average value of the fiber core brightness signal in the reference solution is the average value of the brightness signal of all fiber core positions extracted at the fiber core position on the average image set in the reference solution, and the average image set in the reference solution is obtained by averaging multiple frames of image data obtained by immersing the endoscope probe into the reference concentration of the sodium fluorescein solution at the maximum laser power.

[0024] In an embodiment, the brightness value in the preset interval of the brightness value is the maximum brightness value that the hardware can achieve multiplied by a coefficient greater than or equal to 0.5 and less than or equal to 1.

[0025] In a second aspect, the application further provides a confocal endoscope laser power automatic adjustment method, comprising:

[0026] The brightness signal value of the fiber core obtained based on the current concentration of the sodium fluorescein solution, the reference concentration of the sodium fluorescein solution obtained by the laser power determination model construction method of any one of the first aspect, the first correspondence relationship and the second correspondence relationship;

[0027] Constructing a model of the current concentration, the laser power and the fiber core brightness, thereby determining the laser power corresponding to the current concentration of the sodium fluorescein solution when the fiber core brightness signal just reaches the maximum brightness value that the hardware can achieve.

[0028] In an embodiment, the model of the current concentration, the laser power and the core brightness is built to determine the laser power corresponding to the current concentration of the sodium fluorescein solution when the core brightness signal just reaches the maximum brightness value of the hardware, which specifically includes:

[0029] The brightness signal value adjustment range is determined according to the upper limit of the maximum brightness value of the hardware, the first adjustment coefficient and the second adjustment coefficient, and the laser power adjustment range is determined according to the maximum laser power and the minimum laser power of the laser;

[0030] The maximum laser power is used as the initial laser power, and the effective image set is obtained;

[0031] The larger brightness value of each frame of image in the effective image set is obtained;

[0032] The current concentration of the sodium fluorescein solution corresponding to the current laser power is calculated based on the average value of the larger brightness value;

[0033] The laser power determination model is built according to the concentration of the sodium fluorescein solution, the core brightness signal value and the laser power, and the laser power when the hardware reaches the maximum brightness value is calculated according to the current concentration of the sodium fluorescein solution;

[0034] The laser power when the brightness signal reaches the maximum value is determined as the adjusted target laser power.

[0035] In an embodiment, the current concentration of the sodium fluorescein solution corresponding to the current laser power is calculated based on the average value of the larger brightness value, which includes:

[0036] The current concentration of the sodium fluorescein solution corresponding to the current laser power is calculated according to the average value of the larger brightness value, the first corresponding relationship fitted and built according to the set of core brightness signals in the air and the set of laser powers, the second corresponding relationship fitted and built according to the set of core brightness signals in the solution and the set of laser powers, and the reference concentration of the sodium fluorescein used in the second corresponding relationship.

[0037] In an embodiment, the method for obtaining the effective image set includes:

[0038] The cache image set is obtained;

[0039] The larger brightness value and the larger gradient value of each frame of image in the cache image set are calculated;

[0040] The cache images in the cache image set are screened based on the larger brightness value and the larger gradient value to obtain the effective image set.

[0041] In summary, the laser power determination model construction method of the embodiment of the present application comprises: selecting K different laser powers to construct a laser power set; obtaining N frames of image data of the above endoscope probe in air under each laser power respectively to construct an air environment image data set; obtaining N frames of image data of the above endoscope probe immersed in a reference concentration of fluorescein sodium solution under each laser power respectively to construct a solution environment image data set; performing data fitting based on the above air environment image data set, the above solution environment image data set, the laser power set and a preset curve fitting method to obtain the above laser power determination model, wherein the laser power determination model comprises a first correspondence relationship and a second correspondence relationship, the first correspondence relationship is the correspondence relationship between air environment image data and the K different laser powers, and the second correspondence relationship is the correspondence relationship between solution environment image data and the K different laser powers. The method proposed in the embodiment of the present application can automatically adjust the laser power according to different environments (air and fluorescent dye solution) by accurately controlling the laser power, and ensure that the best image quality can be obtained under various conditions. This method can effectively cope with individual differences and changes in the concentration of fluorescent dyes, ensure that the brightness and contrast of the image are moderate, and thus more easily identify details and lesions. Automatic laser power adjustment reduces the burden of physicians when operating the confocal endoscope. Physicians do not need to deeply understand how to adjust the laser power according to the image, which reduces the training requirements for physicians and reduces human errors in the operation process. Through the model proposed in the present application, the laser power can be automatically adjusted by applying the model, which can shorten the adjustment time of the equipment and speed up the diagnosis process. The model in the present application can adapt to different types of confocal endoscopes and various clinical environments. The universality of the model makes it easy to integrate into different hardware and software configurations, providing a wider range of applications. The embodiment of the present application establishes a laser power determination model based on actual image data, realizes automatic laser power adjustment of the confocal endoscope in clinical use, effectively improves the image quality and operation efficiency, and reduces the complexity and training requirements of physician operation, providing a more efficient and accurate diagnostic tool for clinical use.

[0042] The confocal endoscope laser power automatic adjusting method of the embodiment of the application comprises: determining a brightness signal value adjusting range according to a maximum brightness value upper limit that can be reached by hardware, a first adjusting coefficient and a second adjusting coefficient, and determining a laser power adjusting range according to a maximum laser power of a laser and the maximum laser power; taking the maximum laser power as an initial laser power, and obtaining an effective image set; obtaining a larger brightness value for each frame of image in the effective image set; and determining a target laser power after adjustment based on an average value of the larger brightness values and the brightness signal value adjusting range. The method proposed in the embodiment of the application realizes automatic adjustment of laser power, so that the endoscope can be automatically adjusted to the best laser output when imaging tissue, thereby improving image quality, simplifying an operation process and reducing the burden of a doctor in operation.

[0043] The laser power determination model construction method and the laser power automatic adjusting method proposed in the application, other advantages, objects and features of the application will be embodied partly through the following description, and will be understood by those skilled in the art through research and practice of the application.

[0044] BRIEF DESCRIPTION OF DRAWINGS

[0045] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The accompanying drawings are intended to illustrate preferred embodiments of the present application, and should not be considered limiting of the present application. Indeed, the drawings can illustrate subject matter not covered by the claims. Like reference numerals are used to indicate like parts throughout the accompanying drawings. In the drawings:

[0046] Fig. 1 is a flow diagram of a laser power determination model construction method provided by an embodiment of the application;

[0047] Fig. 2 is a flow diagram of a confocal endoscope laser power automatic adjusting method provided by an embodiment of the application;

[0048] Fig. 3 is a schematic diagram of an operator structure provided by an embodiment of the application;

[0049] Fig. 4 is a schematic diagram of another operator structure provided by an embodiment of the application;

[0050] Fig. 5 is a schematic diagram of still another operator structure provided by an embodiment of the application;

[0051] Fig. 6 is a schematic diagram of yet another operator structure provided by an embodiment of the application.

[0052] DETAILED DESCRIPTION

[0053] The terms "first", "second", "third", "fourth", and the like in the description and in the claims of the present application and above-mentioned drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a specific sequential or chronological order. It is to be understood that the use of the terms so construed herein is merely for convenience and only to aid in understanding the application and is in no way a limitation on its broader scope. It is also to be understood that the use of relational terms such as first, second and third, and the like do not denote a most preferred or optimum sequence or order. Embodiments of the present application will be described below with reference to the accompanying drawings, which are used to illustrate the embodiments of the present application. It is to be understood that the present application is not limited to the embodiments of the present application described below, but encompasses all possible embodiments within the spirit and scope of the present application.

[0054] Referring to FIG. 1, a flowchart of a method for constructing a laser power determination model according to an embodiment of the present application is shown. The method can include the following steps:

[0055] S110, selecting K different laser powers to construct a laser power set;

[0056] For example, K different laser powers are selected to construct a laser power set . .

[0057] S120, acquiring N frames of image data of the endoscope probe in air at each laser power, respectively, to construct an air environment image data set;

[0058] For example, the endoscope probe captures N frames of image data in air at K different laser power settings, respectively, to form an air environment image data set . .

[0059] S130, acquiring N frames of image data of the endoscope probe immersed in a reference concentration of sodium fluorescein solution at each laser power, respectively, to construct a solution environment image data set;

[0060] For example, similar to step S120, but this time the probe is immersed in a reference concentration of sodium fluorescein solution. Similarly, N frames of image data are captured at K different laser power settings to establish a solution environment image data set .

[0061] S140, data fitting is performed based on the above air environment image dataset, the above solution environment image dataset, the laser power set and a preset curve fitting method to obtain the above laser power determination model, wherein the laser power determination model comprises a first corresponding relationship and a second corresponding relationship, the first corresponding relationship is a corresponding relationship between air environment image data and the K different laser powers, and the second corresponding relationship is a corresponding relationship between solution environment image data and the K different laser powers.

[0062] For example, based on the first two datasets (air environment and solution environment image datasets) and different laser powers, a preset curve fitting method is used for data analysis and fitting. Through this method, a laser power determination model is established, which includes two corresponding relationships:

[0063] The first corresponding relationship f1 is the relationship between air environment image data and different laser powers.

[0064] The second corresponding relationship f2 is the relationship between solution environment image data and different laser powers.

[0065] In summary, the method proposed in the embodiments of the present application can automatically adjust the laser power according to different environments (air and fluorescent dye solution) by precisely controlling the laser power, ensuring that the best image quality can be obtained under various conditions. This method can effectively cope with individual differences and changes in fluorescent dye concentration, ensuring that the brightness and contrast of the image are moderate, so that details and lesions can be more easily identified. Automatic laser power adjustment reduces the burden on physicians when operating a confocal endoscope. Physicians do not need to have a deep understanding of how to adjust the laser power according to the image, which reduces the training requirements for physicians and reduces human errors during operation. Through the model proposed in the present application, the laser power can be automatically adjusted by applying the model, which can shorten the adjustment time of the equipment and speed up the diagnosis process. The model in the present application can adapt to different types of confocal endoscopes and various clinical environments. The universality of the model makes it easy to integrate into different hardware and software configurations, providing a wider range of applications. The embodiments of the present application establish a laser power determination model based on actual image data, realize automatic laser power adjustment of the confocal endoscope in clinical use, effectively improve the image quality and operation efficiency, and at the same time reduce the complexity and training requirements of physician operation, providing a more efficient and accurate diagnostic tool for clinical use.

[0066] In some examples, the data fitting based on the above air environment image dataset, the above solution environment image dataset, the laser power set and the preset curve fitting method to obtain the above laser power determination model comprises:

[0067] Based on the average value of the brightness signal values of all the core positions under each laser power in the above air environment image data set, an air core brightness signal average value set is constructed .

[0068] Based on the average value of the brightness signal values of all the core positions under each laser power in the above solution environment image data set, a solution core brightness signal average value set is constructed .

[0069] According to the above air core brightness signal average value set, the above laser power set and the above preset curve fitting method, data fitting is performed to construct the above first correspondence relationship;

[0070] According to the above solution core brightness signal average value set, the above laser power set and the above preset curve fitting method, data fitting is performed to construct the above second correspondence relationship;

[0071] According to the above first correspondence relationship and the above second correspondence relationship, the above laser power determination model is created.

[0072] For example, the air environment image data set is averaged according to the pixel area to obtain an air average image set under all laser powers , and the average value of the brightness signal values at all the cores is extracted , denoted as the air core brightness signal average value set , wherein .

[0073] The solution environment image data set is averaged to obtain a fluorescein sodium solution average image set under all laser powers ; the average value of the brightness signal values at all the cores is extracted from to form a solution core brightness signal average value set , wherein .

[0074] The laser power set and the air core brightness signal average value set are used for fitting to obtain , and f1 is the first correspondence relationship.

[0075] The laser power set and the solution core brightness signal average value set are used for fitting to obtain , and f2 is the second correspondence relationship.

[0076] The laser power determination model is a model comprising the first correspondence relationship and the second correspondence relationship.

[0077] In some examples, further comprising:

[0078] Positioning the above-mentioned fiber core to obtain a fiber core position.

[0079] In some examples, the above-mentioned fiber core is positioned using the above-mentioned air environment image dataset or the above-mentioned solution environment image dataset.

[0080] In some examples, the above-mentioned fiber core position is obtained by calculating the average value of the brightness signal value of the fiber core and the average value of the brightness signal value of the fiber core in the solution.

[0081] In some examples, the above-mentioned fiber core position is obtained by calculating the average value of the brightness signal value of the fiber core and the average value of the brightness signal value of the fiber core in the solution.

[0082] In some examples, the above-mentioned fiber core position is obtained by calculating the average value of the brightness signal value of the fiber core and the average value of the brightness signal value of the fiber core in the solution. Image set of mean values ​​in solution ;

[0083] Extract the average value set of fiber core brightness signal in the air at the fiber core location located on the aforementioned average image set in the air;

[0084] The average value set of fiber core brightness signal in the solution is extracted from the fiber core location located on the mean image set in the above solution.

[0085] For example, data collected at each laser power. The frame data is averaged pixel by pixel. This yields a set of average image values ​​in air for all laser powers. Image set of mean values ​​in sodium fluorescein solution ;

[0086] use All fiber cores are located using the fiber core positioning method.

[0087] exist The average value of the signal at all fiber cores is extracted using the above-mentioned fiber core positioning results, and denoted as . The set of average signal values ​​at the fiber core in air under all laser powers. ;Depend on Extract the average value of the signal at all fiber cores. The average signal set at the fiber core in air under all laser powers .

[0088] In some examples, the above reference concentration is the average core brightness signal in the reference solution. Within the preset range of brightness values, the average brightness signal of the fiber core in the aforementioned reference solution is the average brightness signal of all fiber core positions extracted from the located fiber core position on the average image set in the reference solution. The aforementioned average image set in the reference solution is obtained by averaging multiple frames of image data obtained by immersing the endoscope probe in the aforementioned reference concentration of fluorescein sodium solution at maximum laser power.

[0089] For example, a sodium fluorescein solution of a certain concentration is prepared, and this concentration is denoted as... Sodium fluorescein is a commonly used fluorescent dye that fluoresces under specific laser irradiation. In this step, the endoscope probe is immersed in this solution and the laser power is adjusted to maximum to ensure that the acquired brightness signal value is within a preset range. This preset range is set according to experimental or clinical needs to ensure image quality and safety. The preset range can be... .

[0090] In some examples, the luminance value in the preset range is the maximum luminance value that the hardware can achieve multiplied by a coefficient greater than or equal to 0.5 and less than or equal to 1.

[0091] For example, the upper limit of the signal value is , the ideal signal value is , the acceptable signal value range is , the maximum laser power is , the minimum laser power is , is the current laser power.

[0092] is the maximum value of the luminance value that can be achieved by the hardware characteristics (such as the number of bits of the AD sampling chip).

[0093] and are determined by the laser itself, which can provide the maximum and minimum laser power.

[0094] , , ,

[0095] Typical values are 0.9, 0.85, 0.95.

[0096] In some examples, the preset curve fitting method includes one or more of linear fitting, piecewise linear fitting, quadratic equation, multiple equation, and log curve.

[0097] For example, the preset curve fitting method is a key step in establishing the laser power determination model. These methods model the relationship between image data and laser power, thereby providing the best laser power settings for the endoscope. These curve fitting methods include linear fitting, piecewise linear fitting, quadratic equation, multiple equation, and log curve. By selecting the appropriate curve fitting method, it can be determined which mathematical model to use based on the specific performance of the experimental or clinical data, thereby accurately establishing the relationship between laser power and image quality.

[0098] In a second aspect, as shown in FIG. 2, the present application also provides a confocal endoscope laser power automatic adjustment method, comprising:

[0099] S210, obtaining a core brightness signal value of the current concentration of sodium fluorescein solution, a reference sodium fluorescein solution concentration obtained by the laser power determination model construction method of any one of the first aspect, a first correspondence relationship and a second correspondence relationship;

[0100] For example, first, the core brightness signal value of the sodium fluorescein solution with the current concentration is measured by the confocal endoscope. This brightness signal value reflects the light intensity of the sodium fluorescein under the excitation of the laser. Using the previously established laser power determination model, which is based on the standard data of sodium fluorescein solutions with different concentrations. The model includes two main parts: the first correspondence relationship (the relationship between the concentration of sodium fluorescein and brightness) and the second correspondence relationship (the relationship between brightness and laser power).

[0101] S220, constructing a model of the current concentration, laser power and core brightness, thereby determining the laser power corresponding to the current concentration of sodium fluorescein solution when the core brightness signal just reaches the maximum brightness value that the hardware can reach.

[0102] For example, according to the real-time data (core brightness) obtained from step S210 and the reference model (sodium fluorescein concentration corresponding to brightness and laser power), a model is constructed to describe the relationship between core brightness and laser power under the current concentration. This model allows dynamic adjustment of laser power based on the actual measured brightness signal value. Using the constructed model, the laser power corresponding to the current concentration of sodium fluorescein solution when the core brightness signal just reaches the maximum brightness value that the hardware can reach is determined. This automatic adjustment ensures that the best imaging effect is achieved under different concentrations, preventing excessive or insufficient laser output.

[0103] In summary, the method proposed in the embodiments of the present application can maximize the imaging quality by precisely adjusting the laser power, improve the accuracy and efficiency of diagnosis. It prevents sample damage or equipment damage caused by excessive laser power, and avoids missing image information due to insufficient brightness. This automatic adjustment method reduces the burden on the operator, making the operation of the confocal endoscope more convenient and safe, especially in complex or long medical examinations.

[0104] In some examples, the constructing a model of the current concentration, laser power and core brightness, thereby determining the laser power corresponding to the current concentration of sodium fluorescein solution when the core brightness signal just reaches the maximum brightness value that the hardware can reach specifically includes:

[0105] determining a brightness signal value adjustment range according to the upper limit of the maximum brightness value that the hardware can reach, a first adjustment coefficient and a second adjustment coefficient, and determining a laser power adjustment range according to the maximum laser power and the minimum laser power of the laser;

[0106] An exemplary range of luminance signal value adjustment is determined according to the set upper limit of luminance signal value and the first and second adjustment coefficients. This range is used as a reference for adjusting laser power in subsequent steps, ensuring that the image luminance signal intensity is within a desired interval, neither too bright nor too dark.

[0107] Specifically, let the upper limit of luminance signal value be , the desired signal value size be , the acceptable signal value size interval be , the maximum laser power be , the minimum laser power be , , and the current laser power be

[0108] is the maximum value of luminance value that can be reached, determined by hardware characteristics (such as the number of bits of the AD sampling chip). and are determined by the laser itself, which can provide the maximum and minimum values of laser power.

[0109] Take the maximum laser power as the initial laser power, and obtain an effective image set;

[0110] An exemplary image set is obtained by collecting images at the current maximum laser power of the endoscope, with the number of image frames being . Let the cached image set be . These images will be used for subsequent analysis and processing, with the goal of evaluating the image quality at maximum power and providing preliminary data for power adjustment. The initially obtained cached image set is filtered to remove images of low quality or that do not meet the analysis requirements. Effective images are selected from the cached images. Due to the inherent characteristics of the confocal endoscope, such as small field of view, high magnification, and short working distance, a portion of the images formed are invalid, such as all-black images when not in contact with tissue, all-white images when in contact too tightly, motion artifacts, etc. Not considering these images when calculating the laser power to be adjusted will make the calculated value more accurate, i.e., closer to the expected value. The filtered image set (filtered image set) contains more representative and analytically valuable images, which are used for further luminance analysis.

[0111] Obtain the larger luminance value for each frame of image in the effective image set;

[0112] An exemplary further analysis in the effective image set extracts the larger luminance value from each frame of image. This step is critical in evaluating the luminance level of the image at maximum power, providing a basis for adjusting the laser power to a more suitable level.

[0113] calculate the current concentration of the sodium fluorescein solution corresponding to the current laser power based on the average of the larger values of the brightness;

[0114] For example, based on the larger values of the brightness extracted from the screening image set and the previously set brightness signal value adjustment range, a target laser power after adjustment is calculated. This new laser power keeps the brightness of the image within the ideal range, improving the usability and diagnostic value of the image.

[0115] Wherein, the larger values can be extracted from the image of all core brightness signal values, the histogram is counted, and the value with a certain percentage from high to low in the histogram is taken as the larger value of the brightness, denoted as 5%. The average of the larger values of the brightness of each frame of image in the screening image set is taken to obtain .

[0116] According to the laser power determination model constructed based on the concentration of the sodium fluorescein solution, the core brightness signal value and the laser power, and the current concentration of the sodium fluorescein solution, the laser power is calculated when the maximum brightness value that the hardware can reach is just reached;

[0117] For example, if and , the brightness is low and the laser power needs to be increased, and the laser power can be increased. First, the current concentration of the sodium fluorescein solution needs to be determined. Through any one of the above laser power determination models and the laser power when the brightness signal reaches the maximum value.

[0118] The laser power when the brightness signal reaches the maximum value is determined as the target laser power after adjustment.

[0119] In some examples, the current concentration of the sodium fluorescein solution corresponding to the current laser power is calculated based on the average of the larger values of the brightness, including:

[0120] According to the average of the larger values of the brightness, the first correspondence relationship fitted and constructed based on the set of core brightness signals in the air and the set of laser powers, the second correspondence relationship fitted and constructed based on the set of core brightness signals in the solution and the set of laser powers, and the reference concentration of sodium fluorescein used in the above second correspondence relationship, the current concentration of the sodium fluorescein solution corresponding to the current laser power is calculated.

[0121] For example, the corresponding sodium fluorescein concentration is calculated as : ;

[0122] The model is established to calculate the concentration of sodium fluorescein just reaches the maximum brightness signal laser power at time t : ;

[0123] adjusting laser power to .

[0124] In some examples, the method for obtaining the set of valid images comprises:

[0125] obtaining a set of buffered images;

[0126] calculating a larger luminance value and a larger gradient value for each frame of image in the set of buffered images;

[0127] selecting a buffered image in the set of buffered images based on the larger luminance value and the larger gradient value to obtain the set of valid images.

[0128] For example, specifically, when selecting valid images, the selection can be based on the following:

[0129] The selection operation can specifically comprise:

[0130] (1) For each frame of buffered image, calculate a larger luminance value and a larger gradient value.

[0131] The method for calculating the larger luminance value is: extract all core luminance signal values from the image, count the histogram, and take the value from high to low cumulative proportion of 5% in the histogram as the larger luminance value, denoted as .

[0132] For example, suppose the histogram result is as follows:

[0133] Luminance signal value 0123456789 Number 3121618151311822

[0134] The total number is 3+5+6+…+2=100. The proportion from high to low is:

[0135] 9: 2 / 100 = 0.02

[0136] 9~8: (2+2) / 100 = 0.04

[0137] 9~7: (2+2+8) / 100 = 0.12

[0138] The proportion of 9~8 is less than 5%, and the proportion of 9~7 is greater than 5%, so the larger luminance signal value from high to low cumulative proportion of 5% is 7.

[0139] The method for calculating the larger gradient value is: convolve the image using the following four 3x3 size operators respectively to obtain , Let

[0140] are the pixel row and column coordinates, respectively. The round function is the nearest rounding, the max function is the maximum value, and the abs function is the absolute value. The histogram of is counted, and the value from high to low cumulative proportion of 5% in the histogram is taken as the larger gradient value.

[0141] The operator used can be any of the four in FIGS. 3-6. The operator used can also be flipped symmetrically according to the row, column, or diagonal where 0 is located.

[0142] (2) The buffered images are filtered according to the larger brightness value and the larger gradient value.

[0143] The larger brightness values of all buffered images are sorted in descending order, and the first half of the buffered images are taken as . The larger gradient values of all buffered images are sorted in descending order, and the first half of the buffered images are taken as . The filtered images are the union of and , that is, The above and the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

[0144] Industrial applicability

[0145] The laser power determination model construction method provided by the embodiments of the present application can automatically adjust the laser power according to different environments (air and fluorescent dye solution) by accurately controlling the laser power, ensuring that the best image quality can be obtained under various conditions. This method can effectively cope with individual differences and changes in fluorescent dye concentration, ensuring that the brightness and contrast of the image are moderate, making it easier to identify details and lesions. The laser power automatic adjustment method implemented by the model construction method provided by another embodiment can automatically adjust to the best laser output, thereby improving image quality, simplifying the operation process, and reducing the burden on doctors during operation. Therefore, the laser power determination model construction method and the laser power automatic adjustment method provided by the embodiments of the present application have industrial applicability.​​​

Claims

1. A method for constructing a laser power determination model, characterized in that, include: Select K different laser powers to construct a laser power set; At each laser power, N frames of image data of the endoscope probe in the air are acquired to construct an air environment image dataset; At each laser power, N frames of image data were acquired of the endoscope probe immersed in a sodium fluorescein solution of a reference concentration to construct a solution environment image dataset. The laser power determination model is obtained by fitting data based on the air environment image dataset, the solution environment image dataset, the laser power set, and a preset curve fitting method. The laser power determination model includes a first correspondence and a second correspondence. The first correspondence is the correspondence between air environment image data and the K different laser powers, and the second correspondence is the correspondence between solution environment image data and the K different laser powers.

2. The laser power determination model construction method according to claim 1, characterized in that, The process of fitting data based on the air environment image dataset, the solution environment image dataset, the laser power dataset, and a preset curve fitting method to obtain the laser power determination model includes: Based on the average brightness signal values ​​of all fiber core locations at each laser power in the aforementioned air environment image dataset, a set of average fiber core brightness signals in the air is constructed. ； Based on the average brightness signal values ​​of all fiber core locations at each laser power in the solution environment image dataset, a set of average brightness signal values ​​of the fiber core in the solution is constructed. ； The data is fitted using the average value set of fiber core brightness signals in the air, the laser power set, and the preset curve fitting method to construct the first correspondence. The second correspondence is constructed by fitting data based on the average value set of fiber core brightness signals in the solution, the laser power set, and the preset curve fitting method. The laser power determination model is created based on the first correspondence and the second correspondence.

3. The laser power determination model construction method according to claim 2, characterized in that, Also includes: The fiber core is located using the air environment image dataset or the solution environment image dataset to obtain the fiber core position.

4. The laser power determination model construction method according to claim 3, characterized in that, The specific methods for obtaining the average value of the brightness signal at the fiber core location and the average value of the fiber core brightness signal in the solution are as follows: In both the air environment image dataset and the solution environment image dataset, the average of N frames of image data acquired at each laser power is calculated pixel-wise to obtain the average image set in the air. Image set of mean values ​​in solution ； Extract the average value set of fiber core brightness signals in the air at the fiber core location located on the average image set in the air; The average value set of fiber core brightness signal in the solution is extracted at the fiber core location located on the mean image set in the solution.

5. The laser power determination model construction method according to claim 4, characterized in that, The reference concentration is the average fiber core brightness signal in the reference solution. Within the preset range of brightness values, the average brightness signal of the fiber core in the reference solution is the average brightness signal of all fiber core positions extracted from the located fiber core position on the average image set in the reference solution. The average image set in the reference solution is obtained by averaging multiple frames of image data obtained by immersing the endoscope probe in the sodium fluorescein solution of the reference concentration at maximum laser power.

6. The laser power determination model construction method according to claim 5, characterized in that, The brightness value in the preset range is the maximum brightness value that the hardware can achieve multiplied by a coefficient that is greater than or equal to 0.5 and less than or equal to 1.

7. A method for automatically adjusting the laser power of a confocal endoscope, characterized in that, The fiber core brightness signal value obtained based on the current concentration of sodium fluorescein solution, the reference sodium fluorescein solution concentration obtained by the laser power determination model construction method according to any one of claims 1-6, the first correspondence relationship, and the second correspondence relationship. A model is constructed based on the current concentration, laser power, and fiber core brightness to determine the laser power corresponding to the current concentration of sodium fluorescein solution when the fiber core brightness signal just reaches the maximum brightness value achievable by the hardware.

8. The method for automatically adjusting the laser power of a confocal endoscope according to claim 7, characterized in that, The process of constructing a model based on the current concentration, laser power, and fiber core brightness to determine the laser power corresponding to the current concentration of sodium fluorescein solution when the fiber core brightness signal just reaches the maximum brightness value achievable by the hardware specifically includes: The brightness signal value adjustment range is determined based on the maximum brightness value that the hardware can achieve, the first adjustment coefficient, and the second adjustment coefficient; the laser power adjustment range is determined based on the maximum laser power and the minimum laser power of the laser. The effective image set is obtained by using the maximum laser power as the initial laser power; For each frame in the valid image set, obtain the larger brightness value; The current concentration of the sodium fluorescein solution corresponding to the current laser power is calculated based on the average of the larger brightness values. The laser power determination model is constructed based on the concentration of sodium fluorescein solution, the brightness signal value of the fiber core, and the laser power. The laser power at which the maximum brightness value that the hardware can just reach is calculated based on the current concentration of sodium fluorescein solution. The laser power at which the brightness signal reaches its maximum value is determined as the adjusted target laser power.

9. The method for automatically adjusting the laser power of a confocal endoscope according to claim 8, characterized in that, The current concentration of the sodium fluorescein solution corresponding to the current laser power is calculated based on the average of the larger brightness values, including: Based on the average value of the larger brightness value, the first correspondence constructed by fitting the fiber core brightness signal set and the laser power set in the air, the second correspondence constructed by fitting the fiber core brightness signal set and the laser power set in the solution, and the reference concentration of sodium fluorescein used in the second correspondence, the current concentration of sodium fluorescein solution corresponding to the current laser power is calculated.

10. The method for automatically adjusting the laser power of a confocal endoscope according to claim 8, characterized in that, The method for obtaining a valid image set includes: Retrieve cached image set; For each frame in the cached image set, calculate the maximum brightness value and the maximum gradient value; The cached images in the cached image set are filtered based on the larger brightness value and the larger gradient value to obtain the effective image set.

Images