System and method for optimizing near-infrared two-region fluorescence imaging

Abstract

The embodiment of the invention provides a system and a method for optimizing near-infrared two-region fluorescence imaging, and belongs to the technical field of image processing. The system comprises a data determination model which is used for determining a fluorescent probe corresponding to a near-infrared second region and a target laser capable of emitting laser of a wave band corresponding to the near-infrared second region; the data processing module is used for introducing the fluorescent probe into a target object and exciting the fluorescent probe by using the target laser so as to enable the fluorescent probe to emit a fluorescent signal of a near-infrared second region corresponding wave band; the data acquisition module is used for collecting a fluorescence signal by using an imaging detector and converting the fluorescence signal into an initial image of a target object; and the data optimization module is used for performing image processing on the initial image to obtain a target image of the target object. The problem that when imaging is carried out in deep tissue, due to the fact that absorption and scattering of near-infrared second-area fluorescence signals are prone to causing a low signal-to-noise ratio to affect the contrast ratio of images, tumor and normal tissue are difficult to distinguish, and operation guiding accuracy is affected is solved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a system and method for optimizing near-infrared second-zone fluorescence imaging. Background Art

[0002] Digestive system tumors are common malignant tumors with high morbidity and mortality rates worldwide. Neoangiogenesis in and around tumor cells, that is, the process of forming new blood vessels from existing blood vessels, provides nutrition to tumor tissues and participates in various subsequent physiological and pathological processes of tumors. In recent years, anti-angiogenesis therapy based on nanotechnology has become a new approach for the treatment of digestive tract tumors. Due to the significant heterogeneity of vascular structure between tumor tissues and general tissues, nanomolecules can more easily penetrate the vascular wall and target tumor tissues. This process requires angiography, but traditional imaging methods are difficult to achieve the required microscopic resolution. In order to achieve the diagnosis and treatment of tumors at the nanoscale, near-infrared fluorescence imaging technology is applied to angiography to more clearly present the heterogeneous characteristics of normal vascular tissues and vascular tissues around tumors. However, when imaging in deep tissues, the existing technology is prone to low signal-to-noise ratio due to the absorption and scattering of near-infrared second-zone fluorescence signals, which affects the contrast and clarity of the image, making it difficult to distinguish tumors from normal tissues, thereby affecting the accuracy of surgical guidance.

[0003] Therefore, it is urgent to design a technical solution to solve at least one of the above technical problems. Summary of the invention

[0004] The main purpose of the embodiments of the present invention is to provide a system and method for optimizing near-infrared zone II fluorescence imaging, aiming to solve the problem that when imaging in deep tissues in the prior art, the absorption and scattering of near-infrared zone II fluorescence signals easily lead to a low signal-to-noise ratio, affecting the contrast and clarity of the image, making it difficult to distinguish between tumors and normal tissues, thereby affecting the accuracy of surgical guidance.

[0005] In a first aspect, an embodiment of the present invention provides a system for optimizing near-infrared second-zone fluorescence imaging, comprising:

[0006] A data determination module, used to determine the fluorescent probe corresponding to the near-infrared region II and a target laser capable of emitting laser light in a wavelength band corresponding to the near-infrared region II;

[0007] A data processing module, used for introducing the fluorescent probe into the target object, and using the target laser to excite the fluorescent probe in the target object, so that the fluorescent probe emits a fluorescent signal in the corresponding band of the near-infrared second region;

[0008] A data acquisition module, used to collect the fluorescence signal using an imaging detector and convert the fluorescence signal into an initial image corresponding to the target object;

[0009] The data optimization module is used to perform image processing on the initial image to obtain a target image corresponding to the target object.

[0010] In a second aspect, an embodiment of the present invention provides a method for optimizing near-infrared second-zone fluorescence imaging, comprising:

[0011] Determine the fluorescent probe corresponding to the second near-infrared region and the target laser capable of emitting the laser light in the corresponding wavelength band of the second near-infrared region;

[0012] Introducing the fluorescent probe into a target object, and using the target laser to excite the fluorescent probe in the target object, so that the fluorescent probe emits a fluorescent signal in a wavelength band corresponding to the second near-infrared region;

[0013] Using an imaging detector to collect the fluorescence signal, and converting the fluorescence signal into an initial image corresponding to the target object;

[0014] The initial image is processed to obtain a target image corresponding to the target object.

[0015] In a third aspect, an embodiment of the present invention further provides a terminal device, comprising a processor, a memory, a computer program stored in the memory and executable by the processor, and a data bus for realizing connection and communication between the processor and the memory, wherein when the computer program is executed by the processor, the steps of any one of the systems for optimizing near-infrared second-zone fluorescence imaging provided in the specification of the present invention are realized.

[0016] In a fourth aspect, an embodiment of the present invention further provides a storage medium for computer-readable storage, characterized in that the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement any step of a system for optimizing near-infrared second-zone fluorescence imaging as provided in the specification of the present invention.

[0017] The embodiment of the present invention provides a system and method for optimizing near-infrared zone II fluorescence imaging. The system determines the fluorescent probe corresponding to the near-infrared zone II and the target laser that can emit the laser of the corresponding band of the near-infrared zone II through the data determination module, and then introduces the fluorescent probe into the target object through the data processing module, and excites the fluorescent probe by the target laser to emit the fluorescence signal of the corresponding band of the near-infrared zone II. In order to better exert the anti-tumor effect of nano-targeted drugs, angiography is indispensable in this application, and traditional imaging methods are difficult to reach this microscopic level. Near-infrared fluorescence imaging technology for angiography can clearly present the heterogeneity characteristics of normal vascular tissue and vascular tissue around tumors. Moreover, since there is almost no autofluorescence in the near-infrared band in the tissue, the use of contrast agents with near-infrared fluorescence can greatly improve the signal-to-background ratio of intraoperative fluorescence signals, improve the accuracy, efficacy and safety of interventional targeted therapy, so that the fluorescence signal is collected by the imaging detector according to the data acquisition module, and converted into the initial image corresponding to the target object, and the initial image is processed according to the data optimization module to obtain the target image corresponding to the target object, thereby improving the signal-to-noise ratio and enhancing the data distinction effect of near-infrared zone II fluorescence imaging. This system has designed a series of optimization strategies based on the characteristics of near-infrared zone II fluorescence imaging, including enhancing light source performance, improving detector sensitivity, and applying efficient image processing algorithms. These measures can still obtain high-definition images when the fluorescence signal is weak, solving the problem of low signal-to-noise ratio caused by the absorption and scattering of near-infrared zone II fluorescence signals in deep tissue imaging in the prior art. These problems affect the contrast and clarity of the image, making it difficult to distinguish between tumors and normal tissues, thereby affecting the accuracy of surgical guidance. By optimizing the system, the present invention can effectively improve the quality and clinical application value of near-infrared zone II fluorescence imaging. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 A schematic diagram of the module structure of a system for optimizing near-infrared second-zone fluorescence imaging provided by an embodiment of the present invention;

[0020] Figure 2 A schematic flow chart of a method for optimizing near-infrared second-zone fluorescence imaging provided by an embodiment of the present invention;

[0021] Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0024] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0025] The embodiment of the present invention provides a system and method for optimizing near-infrared second-zone fluorescence imaging. The system for optimizing near-infrared second-zone fluorescence imaging can be applied to a terminal device, which can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0026] Digestive system tumors are common malignant tumors with high morbidity and mortality rates worldwide. Neoangiogenesis in and around tumor cells, that is, the process of forming new blood vessels from existing blood vessels, provides nutrition to tumor tissues and participates in various subsequent physiological and pathological processes of tumors. In recent years, anti-angiogenesis therapy based on nanotechnology has become a new approach for the treatment of digestive tract tumors. Due to the significant heterogeneity of vascular structure between tumor tissues and general tissues, nanomolecules can more easily penetrate the vascular wall and target tumor tissues. This process requires angiography, but traditional imaging methods are difficult to achieve the required microscopic resolution. In order to achieve the diagnosis and treatment of tumors at the nanoscale, near-infrared fluorescence imaging technology is applied to angiography to more clearly present the heterogeneous characteristics of normal vascular tissues and vascular tissues around tumors. However, when imaging in deep tissues, the existing technology is prone to low signal-to-noise ratio due to the absorption and scattering of near-infrared second-zone fluorescence signals, which affects the contrast and clarity of the image, making it difficult to distinguish tumors from normal tissues, thereby affecting the accuracy of surgical guidance.

[0027] Therefore, it is urgent to design a technical solution to solve at least one of the above technical problems.

[0028] To this end, an embodiment of the present invention provides a system and method for optimizing near-infrared zone II fluorescence imaging. The system determines the fluorescent probe corresponding to the near-infrared zone II and the target laser that can emit the laser of the corresponding band of the near-infrared zone II through the data determination module, and then introduces the fluorescent probe into the target object through the data processing module, and uses the target laser to excite the fluorescent probe so that it emits a fluorescence signal of the corresponding band of the near-infrared zone II. In order to better exert the anti-tumor effect of nano-targeted drugs, angiography is indispensable in this application, and traditional imaging methods are difficult to reach this microscopic level. Near-infrared fluorescence imaging technology for angiography can clearly present the heterogeneity characteristics of normal vascular tissue and vascular tissue around tumors. Moreover, since there is almost no autofluorescence in the near-infrared band in the tissue, the use of contrast agents with near-infrared fluorescence can greatly improve the signal-to-background ratio of intraoperative fluorescence signals, and improve the accuracy, efficacy and safety of interventional targeted therapy, so that the fluorescence signal is collected by the imaging detector according to the data acquisition module, and converted into the initial image corresponding to the target object, and the initial image is processed according to the data optimization module to obtain the target image corresponding to the target object, thereby improving the signal-to-noise ratio and enhancing the data distinction effect of near-infrared zone II fluorescence imaging. This system has designed a series of optimization strategies based on the characteristics of near-infrared zone II fluorescence imaging, including enhancing light source performance, improving detector sensitivity, and applying efficient image processing algorithms. These measures can still obtain high-definition images when the fluorescence signal is weak, solving the problem of low signal-to-noise ratio caused by the absorption and scattering of near-infrared zone II fluorescence signals in deep tissue imaging in the prior art. These problems affect the contrast and clarity of the image, making it difficult to distinguish between tumors and normal tissues, thereby affecting the accuracy of surgical guidance. By optimizing the system, the present invention can effectively improve the quality and clinical application value of near-infrared zone II fluorescence imaging.

[0029] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0030] Please refer to Figure 1 , Figure 1 A schematic diagram of the module structure of a system for optimizing near-infrared second-zone fluorescence imaging provided by an embodiment of the present invention.

[0031] like Figure 1As shown, the system 200 for near-infrared zone II fluorescence imaging optimization includes a data determination module 201, a data processing module 202, a data acquisition module 203, and a data optimization module 204, wherein the data determination module 201 is used to determine the fluorescent probe corresponding to the near-infrared zone II and the target laser that can emit the laser of the corresponding band of the near-infrared zone II; the data processing module 202 is used to introduce the fluorescent probe into the target object, and use the target laser to excite the fluorescent probe in the target object so that the fluorescent probe emits a fluorescent signal of the corresponding band of the near-infrared zone II; the data acquisition module 203 is used to collect the fluorescent signal by using an imaging detector, and convert the fluorescent signal into an initial image corresponding to the target object; the data optimization module 204 is used to perform image processing on the initial image to obtain a target image corresponding to the target object.

[0032] Exemplarily, the main task of the data determination module 201 is to identify and select fluorescent probes and corresponding target lasers suitable for near-infrared zone II fluorescence imaging. Determine the fluorescent probe from the probes that can emit near-infrared zone II (usually 1000-1700 nanometers) fluorescent signals, and ensure the biocompatibility and targeting of the fluorescent probe, and ensure its safety and effectiveness in vivo. Select a target laser that can emit the corresponding band of near-infrared zone II, and ensure that its wavelength, power and stability meet the imaging requirements.

[0033] Exemplarily, the data processing module 202 injects the fluorescent probe into the target object (target object such as a tissue sample or a living body) by a suitable administration method. For example, the target object is introduced by intravenous injection, local injection or the combination of the fluorescent probe and the targeting molecule. The data processing module 202 sets the working parameters of the target laser, such as wavelength, pulse width and power, to ensure effective excitation of the fluorescent probe, and adopts a suitable laser irradiation method (such as point scanning, surface scanning or continuous irradiation), which is adjusted according to the geometric shape and size of the target object, so as to perform fluorescence excitation according to the target laser, so that the fluorescent probe contained in the target object emits a fluorescent signal.

[0034] Exemplarily, the data acquisition module 203 uses an imaging detector to collect fluorescent signals and converts them into an initial image. For example, the data acquisition module 203 selects a near-infrared imaging detector with high sensitivity and high resolution to ensure that weak fluorescent signals can be captured. In addition, the response time, dynamic range, and noise level of the imaging detector can also be considered to meet different imaging requirements. For example, the exposure time, gain, and filter of the imaging detector are set to optimize the signal acquisition effect, so that the fluorescent signal is captured by a near-infrared camera or spectrometer, and displayed or recorded as an initial image in real time.

[0035] Exemplarily, the data optimization module 204 processes the acquired initial image to obtain a high-quality target image.

[0036] For example, the data optimization module 204 performs denoising, background subtraction, and illumination correction on the initial image to reduce noise and artifacts during the imaging process, and uses image enhancement techniques (such as histogram equalization, contrast adjustment, etc.) to improve the contrast and clarity of the image, thereby obtaining a target image.

[0037] Specifically, through the above steps, the whole process from fluorescent probe selection to image optimization can be realized, and high-quality near-infrared zone II fluorescence imaging can be obtained, thereby providing reliable technical support for medical diagnosis and treatment. In addition, in order to better exert the anti-tumor effect of nano-targeted drugs in this application, angiography is indispensable, and traditional imaging methods are difficult to reach this microscopic level. Near-infrared fluorescence imaging technology is used for angiography, which can clearly present the heterogeneous characteristics of normal vascular tissue and vascular tissue around tumors. Moreover, since there is almost no autofluorescence in the near-infrared band in the tissue, the use of contrast agents with near-infrared fluorescence can greatly improve the signal-to-background ratio of intraoperative fluorescence signals, and improve the accuracy, efficacy and safety of interventional targeted therapy.

[0038] In some embodiments, the data optimization module includes: an image processing module, used to perform image denoising on the initial image to obtain a denoised image corresponding to the initial image; an image enhancement module, used to perform image enhancement on the denoised image to obtain the target image corresponding to the denoised image.

[0039] Exemplarily, the data optimization module includes an image processing module and an image enhancement module.

[0040] Exemplarily, the image processing module selects a suitable denoising algorithm according to the noise characteristics in the initial image, such as mean filtering, median filtering or Gaussian filtering, wavelet transform, deep learning method, etc., so as to process the initial image using the selected denoising technology. Ensure that the image details and edge information are maintained during the processing, and do not cause excessive smoothing, so as to obtain a denoised image.

[0041] Exemplarily, the image enhancement module selects a suitable processing algorithm such as contrast enhancement, edge enhancement, detail enhancement, etc. according to the enhancement target, and applies the selected enhancement algorithm to the denoised image to generate a target image.

[0042] Specifically, through the above steps, the denoising and enhancement processing of the initial image can be achieved, and finally a high-quality target image can be obtained, providing reliable visual data support for subsequent analysis or diagnosis.

[0043] In some embodiments, the image processing module includes: an image transformation module, which is used to perform wavelet transform on the initial image to obtain initial wavelet coefficients corresponding to the initial image, and calculate the noise variance corresponding to the initial image based on the initial wavelet coefficients; a threshold calculation module, which is used to determine the target wavelet threshold based on the initial wavelet coefficients and the noise variance; an approximate estimation module, which is used to use the target wavelet threshold to perform approximate estimation on the initial wavelet coefficients to obtain the target wavelet coefficients; and an image denoising module, which is used to reconstruct the image based on the target wavelet coefficients to obtain the denoised image corresponding to the initial image.

[0044] Exemplarily, the image transformation module selects the corresponding wavelet basis function such as Haar, Daubechies, Symlets, etc. according to the characteristics of the initial image and the denoising requirements, and then performs wavelet transformation on the initial image according to the wavelet function to obtain the initial wavelet coefficients. The image transformation module estimates the noise variance in the initial image by analyzing the detail coefficients corresponding to the high-frequency subbands in the initial wavelet coefficients after the wavelet transformation.

[0045] Exemplarily, the threshold calculation module first obtains the image length and image width corresponding to the initial image, and then multiplies the image length and image width to obtain the signal length corresponding to the initial image, and then takes the natural logarithm of the signal length to obtain the logarithm value, and then takes the square root of the logarithm value and multiplies it by the noise variance to obtain the target wavelet threshold.

[0046] Exemplarily, the approximate estimation module uses the target wavelet threshold in combination with the soft threshold function to perform an approximate estimation on the initial wavelet coefficients to obtain the target wavelet coefficients.

[0047] For example, according to the calculated target wavelet threshold, the initial wavelet coefficients are thresholded. For the soft threshold function, the target wavelet threshold is subtracted or added to each initial wavelet coefficient; for the hard threshold function, only the initial wavelet coefficients greater than the target wavelet threshold are retained. Thus, the wavelet coefficients after the target wavelet threshold processing are used as the target wavelet coefficients. The target wavelet coefficients reflect the characteristics of the denoised image.

[0048] Exemplarily, the image denoising module reconstructs the image according to the target wavelet coefficients to obtain a denoised image. For example, the image denoising module performs an inverse wavelet transform using the target wavelet coefficients to restore the denoised image after denoising. The inverse transform process is the opposite of the wavelet transform process, and the target wavelet coefficient combination is restored to the denoised image.

[0049] Specifically, through the above steps, image denoising processing based on wavelet transform can be implemented to obtain a clear denoised image, thereby improving image quality and the accuracy of subsequent analysis.

[0050] In some embodiments, the approximate estimation module includes: a function determination module, which is used to determine the hyperbolic tangent function and the adjustment parameters, and calculate the first function value corresponding to the initial wavelet coefficient under the hyperbolic tangent function; a data comparison module, which is used to obtain the absolute value of the initial wavelet coefficient to obtain the absolute wavelet coefficient, and compare the absolute wavelet coefficient with the target wavelet threshold to obtain a comparison result; a first processing module, which is used to calculate the first difference between the absolute wavelet coefficient and the target wavelet threshold when the comparison result is that the absolute wavelet coefficient is greater than the target wavelet threshold, and calculate the first exponent value corresponding to the first difference under the natural exponent; a ratio calculation module, which is used to calculate the ratio between the target wavelet threshold and the first exponent value to obtain a first ratio result; a ratio adjustment module , used to adjust the first ratio result by using the adjustment parameter to obtain a second ratio result; a first result module, used to calculate the difference between the absolute wavelet coefficient and the second ratio result to obtain a third difference, and multiply the third difference and the first function value to obtain the target wavelet coefficient; a second processing module, used to calculate the second difference between the initial wavelet coefficient and the target wavelet threshold when the comparison result is that the absolute wavelet coefficient is less than or equal to the target wavelet threshold; a difference adjustment module, used to adjust the second difference by using the adjustment parameter to obtain a fourth difference, and calculate the second exponent value corresponding to the fourth difference under the natural exponent; a second result module, used to multiply the second exponent value and the first function value to obtain the target wavelet coefficient.

[0051] Exemplarily, the approximate estimation module includes a function determination module, a data comparison module, a first processing module, a ratio calculation module, a first result module, a second processing module, a difference adjustment module, and a second result module.

[0052] Exemplarily, the function determination module determines a hyperbolic tangent function, which can be smoother and more continuous when processing wavelet coefficients, and sets adjustment parameters for subsequent calculation and adjustment processes, and the adjustment parameters are positive numbers less than 1. The initial wavelet coefficients are used as input and applied to the hyperbolic tangent function to calculate the first function value corresponding to the initial wavelet coefficients in the hyperbolic tangent function.

[0053] Exemplarily, the data comparison module takes the absolute value of the initial wavelet coefficient to obtain the absolute wavelet coefficient, and then compares the absolute wavelet coefficient with the target wavelet threshold to obtain a comparison result, which includes whether the absolute wavelet coefficient is greater than, less than or equal to the target wavelet threshold.

[0054] Exemplarily, when the absolute wavelet coefficient is greater than the target wavelet threshold, the first processing module subtracts the target wavelet threshold from the absolute wavelet coefficient to obtain a first difference, thereby applying the first difference to the natural exponential function to obtain a corresponding first exponential value.

[0055] Exemplarily, the ratio calculation module divides the target wavelet threshold and the first exponent value to obtain a first ratio result.

[0056] Exemplarily, the ratio adjustment module multiplies the first ratio result by the previously set adjustment parameter to obtain the second ratio result.

[0057] Exemplarily, the first result module calculates a third difference between the absolute wavelet coefficient and the second ratio result, and then multiplies the third difference by the first function value to obtain a target wavelet coefficient corresponding to the initial wavelet coefficient when the absolute wavelet coefficient is greater than the target wavelet threshold.

[0058] Exemplarily, when the absolute wavelet coefficient is less than or equal to the target wavelet threshold, the second processing module subtracts the target wavelet threshold from the initial wavelet coefficient to obtain a second difference between the initial wavelet coefficient and the target wavelet threshold.

[0059] Exemplarily, the difference adjustment module obtains a fourth difference by multiplying the adjustment parameter with the second difference, and applies the fourth difference to a natural exponential function to obtain a corresponding second exponential value.

[0060] Exemplarily, the second result module multiplies the second exponent value and the first function value to obtain a target wavelet coefficient corresponding to the initial wavelet coefficient when the absolute wavelet coefficient is less than or equal to the target wavelet threshold.

[0061] Specifically, by processing the initial wavelet coefficients using the hyperbolic tangent function and adjustment parameters, the noise in the image can be removed more effectively. The hyperbolic tangent function has nonlinear characteristics and can better adapt to noises of different intensities and types, thereby improving the accuracy and effect of denoising. The introduction of adjustment parameters makes the processing process more flexible, and the parameters can be adjusted according to different image and noise characteristics to achieve the best denoising effect. This flexibility makes the method applicable to a variety of different scenarios and needs. The method shows strong adaptability by comparing the absolute wavelet coefficients with the target wavelet threshold and adopting different processing strategies according to the comparison results. This adaptability enables the algorithm to perform personalized processing for different wavelet coefficients, thereby improving the accuracy and efficiency of denoising. This can significantly improve the effect and quality of image denoising, while retaining important details of the image, providing a better data foundation for subsequent image processing and analysis.

[0062] In some embodiments, the image enhancement module includes: a window processing module, which is used to determine a target window and determine a window area corresponding to each target pixel in the denoised image under the target window; a variance calculation module, which is used to perform variance calculation on the window area to obtain the window variance corresponding to the target pixel; a weight calculation module, which is used to determine an adjustment factor corresponding to the target pixel in the denoised image according to the window variance, and determine a pixel weight corresponding to the target pixel according to the adjustment factor and the window variance; a distribution calculation module, which is used to determine a target weight corresponding to an initial histogram corresponding to the denoised image according to the pixel weight, and determine a target histogram corresponding to the denoised image according to the target weight; a contrast enhancement module, which is used to determine a corresponding cumulative distribution function according to the target histogram, and perform image enhancement processing on the denoised image according to the cumulative distribution function to obtain the target image.

[0063] Exemplarily, the image enhancement module includes a window processing module, a variance calculation module, a weight calculation module, a distribution calculation module, and a contrast enhancement module.

[0064] Exemplarily, the window processing module determines the target window size such as 3x3, 5x5, 7x7, etc. Thus, for each target pixel in the denoised image, all pixels within the target window range are determined with the target pixel as the center to obtain the corresponding window area. In addition, when processing the image boundary, ensure that the target window does not completely exceed the image range. Boundary pixels can be processed by mirror filling, repeating boundary pixels, etc.

[0065] Exemplarily, the variance calculation module averages all pixel values ​​in the window area, calculates the difference between each pixel value in the window area and the mean, sums the squares of all differences and divides them by the number of pixels in the window area to obtain the window variance corresponding to the target pixel in the window area.

[0066] Exemplarily, the weight calculation module determines the first parameter and the second parameter, and then calculates the maximum and minimum values ​​of the window variance corresponding to all target pixels to obtain the maximum variance and the minimum variance, and then calculates the difference according to the maximum variance and the minimum variance to obtain the variance difference, and then calculates the ratio of the first variance and the variance difference to obtain the first factor. Then, the first factor is multiplied by the minimum variance to obtain the target product, and then the second parameter is subtracted from the target product to obtain the first factor, wherein the first parameter and the second parameter can be set according to historical experience, and the first parameter and the second parameter can be positive or negative, so that the first factor and the second factor are jointly determined as the adjustment factor.

[0067] Exemplarily, the weight calculation module multiplies the first factor by the window variance corresponding to the target pixel and then multiplies the result by the second factor to obtain a target parameter corresponding to the target pixel, thereby substituting the target parameter into the sigmoid function to obtain a pixel weight corresponding to the target pixel.

[0068] Exemplarily, the distribution calculation module performs normalization calculation on the pixel weights to obtain the target weight corresponding to the initial histogram corresponding to the denoised image. The initial histogram consists of each target pixel and the number of target pixels. The target weight is the final weight corresponding to each target pixel in the initial histogram, and then the target histogram corresponding to the denoised image is determined according to the target weight.

[0069] Exemplarily, the contrast enhancement module calculates the cumulative distribution function according to the target histogram, and the cumulative distribution function represents the cumulative probability distribution of the pixel value. Thus, the cumulative distribution function is used to map each pixel in the denoised image, and the pixel value is adjusted to a new pixel value. The mapping process will enhance the contrast of the image. Thus, according to the mapped pixel value, an enhanced target image is generated.

[0070] Specifically, through the above steps, the local contrast enhancement of the denoised image can be achieved, the image quality and visual effect can be improved, and better image data can be provided for subsequent analysis or presentation.

[0071] In some embodiments, the distribution calculation module includes: a pixel acquisition module, which is used to determine the pixel range corresponding to the denoised image, and obtain any pixel value from the pixel range as the current pixel value; a weight summation module, which is used to obtain the associated weight corresponding to the current pixel value from the pixel weight, and sum the associated weights to obtain the first weight sum value corresponding to the current pixel value; a weight processing module, which is used to obtain the first weight sum value corresponding to each of the current pixel values ​​in the pixel range, and sum all the first weight sum values ​​to obtain the second weight sum value; a result acquisition module, which is used to determine the target weight corresponding to the current pixel value according to the first weight sum value and the second weight sum value; wherein the target weight is obtained according to the following formula:

[0072]

[0073] Wherein, M represents the image length corresponding to the denoised image, N represents the image width corresponding to the denoised image, a1 and a2 represent adjustment parameters, var1(x,y) represents the normalized value of the window variance corresponding to the current pixel value when the horizontal position is x and the vertical coordinate is y in the denoised image, IF(img(x,y)=i,1,0) represents that the pixel value of the denoised image img when the horizontal position is x and the vertical coordinate is y is equal to the current pixel value i and takes 1, and the pixel value of the denoised image img when the horizontal position is x and the vertical coordinate is y is not equal to the current pixel value i and takes 0, m represents the lower limit value corresponding to the pixel range, n represents the upper limit value corresponding to the pixel range, var(x,y) represents the window variance corresponding to the current pixel value when the horizontal position is x and the vertical coordinate is y in the denoised image, max(var(x,y)) represents the maximum value corresponding to the window variance in the denoised image, and min(var(x,y)) represents the minimum value corresponding to the window variance in the denoised image.

[0074] Exemplarily, the distribution calculation module includes: a pixel acquisition module, a weight summation module, a weight processing module and a result acquisition module.

[0075] Exemplarily, the pixel acquisition module analyzes the pixel range of all pixels in the denoised image, where the pixel range is between the minimum pixel value and the maximum pixel value, and sequentially acquires each pixel value from the pixel range by traversing to determine it as the current pixel value.

[0076] Exemplarily, the weight summing module searches for all weights corresponding to the current pixel value from the previously calculated pixel weights to obtain the associated weights, which are all weights corresponding to the pixel value corresponding to the target pixel in the pixel weights when it is equal to the current pixel value. The associated weights may be information of multiple pixel weights. All associated weights are summed to obtain the first weight sum corresponding to the current pixel value. The first weight sum is obtained according to the following formula:

[0077]

[0078] Among them, s irepresents the first weight and value corresponding to the current pixel value i, M represents the image length corresponding to the denoised image, N represents the image width corresponding to the denoised image, a1 and a2 represent adjustment parameters, var1(x,y) represents the normalized value of the window variance corresponding to the current pixel value when the horizontal position is x and the vertical coordinate is y in the denoised image, IF(img(x,y)=i,1,0) means that when the pixel value of the denoised image img when the horizontal position is x and the vertical coordinate is y is equal to the current pixel value i, it takes 1, and when the pixel value of the denoised image img when the horizontal position is x and the vertical coordinate is y is not equal to the current pixel value i, it takes 0, var(x,y) represents the window variance corresponding to the current pixel value when the horizontal position is x and the vertical coordinate is y in the denoised image, max(var(x,y)) represents the maximum value corresponding to the window variance in the denoised image, and min(var(x,y)) represents the minimum value corresponding to the window variance in the denoised image.

[0079] Exemplarily, the weight processing module traverses each pixel value within the pixel range, takes it as the current pixel value, obtains its corresponding first weight sum value according to the method of the weight summation module, and sums all the first weight sum values ​​to obtain the second weight sum value.

[0080]

[0081] Wherein, sum represents the second weighted sum value, M represents the image length corresponding to the denoised image, N represents the image width corresponding to the denoised image, a1 and a2 represent adjustment parameters, var1(x,y) represents the normalized value of the window variance corresponding to the current pixel value when the horizontal position is x and the vertical coordinate is y in the denoised image, IF(img(x,y)=i,1,0) represents that the pixel value of the denoised image img when the horizontal position is x and the vertical coordinate is y is equal to the current pixel value i, and the pixel value of the denoised image img when the horizontal position is x and the vertical coordinate is y is 0, m represents the lower limit value corresponding to the pixel range, n represents the upper limit value corresponding to the pixel range, var(x,y) represents the window variance corresponding to the current pixel value when the horizontal position is x and the vertical coordinate is y in the denoised image, max(var(x,y)) represents the maximum value corresponding to the window variance in the denoised image, and min(var(x,y)) represents the minimum value corresponding to the window variance in the denoised image.

[0082] Exemplarily, the result obtaining module calculates the ratio of the first weight sum value corresponding to the current pixel value to the second weight sum value to obtain the target weight corresponding to the current pixel value. The target weight is obtained according to the following formula:

[0083]

[0084] Wherein, M represents the image length corresponding to the denoised image, N represents the image width corresponding to the denoised image, a1 and a2 represent adjustment parameters, var1(x,y) represents the normalized value of the window variance corresponding to the current pixel value when the horizontal position is x and the vertical coordinate is y in the denoised image, IF(img(x,y)=i,1,0) represents that the pixel value of the denoised image img when the horizontal position is x and the vertical coordinate is y is equal to the current pixel value i, and the pixel value of the denoised image img when the horizontal position is x and the vertical coordinate is y is 0, m represents the lower limit value corresponding to the pixel range, n represents the upper limit value corresponding to the pixel range, var(x,y) represents the window variance corresponding to the current pixel value when the horizontal position is x and the vertical coordinate is y in the denoised image, max(var(x,y)) represents the maximum value corresponding to the window variance in the denoised image, and min(var(x,y)) represents the minimum value corresponding to the window variance in the denoised image.

[0085] Specifically, by calculating the first weight and value of each pixel value respectively and summing all the first weights and values, the target weight of each pixel value can be calculated more accurately. This step-by-step summation method can avoid the accumulation of errors that may occur in a single calculation process, thereby improving the accuracy of weight calculation. By accurately calculating the target weight of each pixel value, the pixel value distribution of the denoised image can be more effectively adjusted. This adjustment can better preserve the details and texture of the image while removing noise, thereby significantly improving the denoising effect. By traversing the pixel range and calculating the first weight and value of each pixel value, the method shows high adaptability. This adaptability enables the algorithm to perform personalized weight adjustments according to different pixel values ​​and noise characteristics, thereby improving the accuracy and efficiency of denoising and providing a better data foundation for subsequent image analysis and processing.

[0086] In some embodiments, the system also includes: an image segmentation module, used to perform image segmentation on the target image to obtain a target area corresponding to the target image; a region classification module, used to classify the target area using an image classification model to obtain a target classification result corresponding to the target area; an image analysis module, used to perform reliability analysis on the target classification result to obtain the reliability of the target classification result; a type determination module, used to determine the target type corresponding to the target area according to the reliability and the target classification result, so that the target doctor can diagnose and treat the target area according to the target type.

[0087] Exemplarily, the system for optimizing near-infrared second-zone fluorescence imaging also includes an image segmentation module, a region classification module, an image analysis module, and a type determination module.

[0088] Exemplarily, the image segmentation module performs image segmentation on the target image according to an image segmentation algorithm such as threshold segmentation, edge detection, region growing, watershed algorithm, a segmentation model based on deep learning, etc., thereby obtaining a segmentation result, and then extracts a region containing a target object from the segmentation result to obtain a target region. The target object is a tumor or other abnormal object relative to normal tissue.

[0089] Exemplarily, the region classification module classifies the target region using an image classification model such as a convolutional neural network (CNN), a support vector machine (SVM), a random forest, etc. The classification model outputs a target classification result corresponding to the target region.

[0090] Exemplarily, the image analysis module uses algorithms such as confidence assessment, credibility score calculation, and uncertainty estimation of the classification model to perform reliability analysis on the target classification result to obtain the reliability of the target classification result.

[0091] Exemplarily, the type determination module determines the target type of the target area according to the reliability and the target classification result. For example, when the reliability is greater than a preset value, the classification type corresponding to the maximum classification probability in the target classification result is determined as the target type; when the reliability is less than or equal to the preset value, a classification model different from the target classification result is selected to reclassify the target area until the reliability is greater than the preset value. Thus, after determining the target type of the target area, the target image and the target type corresponding to the target area are sent to the target doctor, so that the target doctor performs subsequent diagnosis and treatment according to the target image and the target type corresponding to the target area.

[0092] Please refer to Figure 2 , Figure 2 A schematic flow chart of another method for optimizing near-infrared second-zone fluorescence imaging provided in an embodiment of the present invention.

[0093] like Figure 2 As shown, the method for optimizing near-infrared second-zone fluorescence imaging includes steps S101 to S104.

[0094] Step S101, determining a fluorescent probe corresponding to the second near-infrared region and a target laser capable of emitting laser light in a wavelength band corresponding to the second near-infrared region.

[0095] Step S102: introducing the fluorescent probe into the target object, and using the target laser to excite the fluorescent probe in the target object, so that the fluorescent probe emits a fluorescent signal in the corresponding band of the second near-infrared region.

[0096] Step S103: using an imaging detector to collect the fluorescence signal, and converting the fluorescence signal into an initial image corresponding to the target object.

[0097] Step S104: performing image processing on the initial image to obtain a target image corresponding to the target object.

[0098] In some implementations, performing image processing on the initial image to obtain a target image corresponding to the target object includes:

[0099] Performing image denoising processing on the initial image to obtain a denoised image corresponding to the initial image;

[0100] Perform image enhancement processing on the denoised image to obtain the target image corresponding to the denoised image.

[0101] In some implementations, performing image denoising on the initial image to obtain a denoised image corresponding to the initial image includes:

[0102] Performing wavelet transform on the initial image to obtain initial wavelet coefficients corresponding to the initial image, and calculating the noise variance corresponding to the initial image according to the initial wavelet coefficients;

[0103] Determine a target wavelet threshold according to the initial wavelet coefficient and the noise variance;

[0104] Using the target wavelet threshold to approximate the initial wavelet coefficients to obtain target wavelet coefficients;

[0105] Image reconstruction is performed according to the target wavelet coefficients to obtain the denoised image corresponding to the initial image.

[0106] In some implementations, the using the target wavelet threshold to approximate the initial wavelet coefficients to obtain the target wavelet coefficients includes:

[0107] Determine a hyperbolic tangent function and an adjustment parameter, and calculate a first function value corresponding to the initial wavelet coefficient under the hyperbolic tangent function;

[0108] Calculating an absolute value of the initial wavelet coefficient to obtain an absolute wavelet coefficient, and comparing the absolute wavelet coefficient with the target wavelet threshold to obtain a comparison result;

[0109] When the comparison result is that the absolute wavelet coefficient is greater than the target wavelet threshold, a first difference between the absolute wavelet coefficient and the target wavelet threshold is calculated, and a first exponent value corresponding to the first difference under a natural exponent is calculated;

[0110] Calculating a ratio between the target wavelet threshold and the first exponent value to obtain a first ratio result;

[0111] Using the adjustment parameter to adjust the first ratio result to obtain a second ratio result;

[0112] Calculating the difference between the absolute wavelet coefficient and the second ratio result to obtain a third difference, and multiplying the third difference by the first function value to obtain the target wavelet coefficient;

[0113] When the comparison result is that the absolute wavelet coefficient is less than or equal to the target wavelet threshold, a second difference between the initial wavelet coefficient and the target wavelet threshold is calculated;

[0114] Using the adjustment parameter to adjust the second difference to obtain a fourth difference, and calculating a second exponent value corresponding to the fourth difference under a natural exponent;

[0115] The second exponent value and the first function value are multiplied to obtain the target wavelet coefficient.

[0116] In some implementations, performing image enhancement processing on the denoised image to obtain the target image corresponding to the denoised image includes:

[0117] Determine a target window, and determine a window area corresponding to each target pixel in the denoised image under the target window;

[0118] Performing variance calculation on the window area to obtain the window variance corresponding to the target pixel;

[0119] Determining an adjustment factor corresponding to the target pixel in the denoised image according to the window variance, and determining a pixel weight corresponding to the target pixel according to the adjustment factor and the window variance;

[0120] Determining a target weight corresponding to an initial histogram corresponding to the denoised image according to the pixel weight, and determining a target histogram corresponding to the denoised image according to the target weight;

[0121] A corresponding cumulative distribution function is determined according to the target histogram, and image enhancement processing is performed on the denoised image according to the cumulative distribution function to obtain the target image.

[0122] In some implementations, determining a target weight corresponding to an initial histogram corresponding to the denoised image according to the pixel weight includes:

[0123] Determine a pixel range corresponding to the denoised image, and obtain any pixel value from the pixel range as a current pixel value;

[0124] Obtaining an associated weight corresponding to the current pixel value from the pixel weights, and summing the associated weights to obtain a first weight sum value corresponding to the current pixel value;

[0125] Obtaining the first weighted sum value corresponding to each of the current pixel values ​​in the pixel range, and summing all of the first weighted sum values ​​to obtain a second weighted sum value;

[0126] Determine the target weight corresponding to the current pixel value according to the first weight sum value and the second weight sum value;

[0127] The target weight is obtained according to the following formula:

[0128]

[0129] Wherein, M represents the image length corresponding to the denoised image, N represents the image width corresponding to the denoised image, a1 and a2 represent adjustment parameters, var1(x,y) represents the normalized value of the window variance corresponding to the current pixel value when the horizontal position is x and the vertical coordinate is y in the denoised image, IF(img(x,y)=i,1,0) represents that the pixel value of the denoised image img when the horizontal position is x and the vertical coordinate is y is equal to the current pixel value i and takes 1, and the pixel value of the denoised image img when the horizontal position is x and the vertical coordinate is y is not equal to the current pixel value i and takes 0, m represents the lower limit value corresponding to the pixel range, n represents the upper limit value corresponding to the pixel range, var(x,y) represents the window variance corresponding to the current pixel value when the horizontal position is x and the vertical coordinate is y in the denoised image, max(var(x,y)) represents the maximum value corresponding to the window variance in the denoised image, and min(var(x,y)) represents the minimum value corresponding to the window variance in the denoised image.

[0130] In some embodiments, the method further comprises:

[0131] Performing image segmentation on the target image to obtain a target area corresponding to the target image;

[0132] Classifying the target area using an image classification model to obtain a target classification result corresponding to the target area;

[0133] Performing reliability analysis on the target classification result to obtain the reliability of the target classification result;

[0134] The target type corresponding to the target area is determined according to the reliability and the target classification result, so that the target doctor can perform diagnosis and treatment on the target area according to the target type.

[0135] In some embodiments, the method for optimizing near-infrared second-zone fluorescence imaging can be applied to a terminal device.

[0136] It should be noted that technicians in the relevant field can clearly understand that for the convenience and conciseness of description, the specific working process of the method for optimizing near-infrared second-zone fluorescence imaging described above can refer to the corresponding process in the aforementioned system embodiment for optimizing near-infrared second-zone fluorescence imaging, and will not be repeated here.

[0137] See also Figure 3 , Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present invention.

[0138] like Figure 3 As shown, the terminal device 300 includes a processor 301 and a memory 302, and the processor 301 and the memory 302 are connected via a bus 303, such as an I2C (Inter-integrated Circuit) bus.

[0139] Specifically, the processor 301 is used to provide computing and control capabilities to support the operation of the entire terminal device. The processor 301 can be a central processing unit (CPU), and the processor 301 can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0140] Specifically, the memory 302 may be a Flash chip, a read-only memory (ROM) disk, an optical disk, a USB flash drive, or a mobile hard disk.

[0141] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a partial structure related to the embodiment of the present invention, and does not constitute a limitation on the terminal device to which the embodiment of the present invention is applied. The specific server may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0142] The processor is used to run a computer program stored in the memory, and implement any one of the systems for optimizing near-infrared second-zone fluorescence imaging provided by the embodiments of the present invention when executing the computer program.

[0143] In one embodiment, the processor is used to run a computer program stored in the memory, and implements the following steps when executing the computer program:

[0144] A data determination module, used to determine the fluorescent probe corresponding to the near-infrared region II and a target laser capable of emitting laser light in a wavelength band corresponding to the near-infrared region II;

[0145] A data processing module, used for introducing the fluorescent probe into the target object, and using the target laser to excite the fluorescent probe in the target object, so that the fluorescent probe emits a fluorescent signal in the corresponding band of the near-infrared second region;

[0146] A data acquisition module, used to collect the fluorescence signal using an imaging detector and convert the fluorescence signal into an initial image corresponding to the target object;

[0147] The data optimization module is used to perform image processing on the initial image to obtain a target image corresponding to the target object.

[0148] In some implementations, the processor 301, during the data optimization module process, executes:

[0149] An image processing module, used for performing image denoising on the initial image to obtain a denoised image corresponding to the initial image;

[0150] The image enhancement module is used to perform image enhancement processing on the denoised image to obtain the target image corresponding to the denoised image.

[0151] In some implementations, the processor 301 performs, during the image processing module process:

[0152] An image transformation module, used for performing wavelet transformation on the initial image to obtain initial wavelet coefficients corresponding to the initial image, and calculating the noise variance corresponding to the initial image according to the initial wavelet coefficients;

[0153] A threshold calculation module, used to determine a target wavelet threshold according to the initial wavelet coefficient and the noise variance;

[0154] An approximate estimation module, used to perform an approximate estimation on the initial wavelet coefficients using the target wavelet threshold to obtain target wavelet coefficients;

[0155] The image denoising module is used to reconstruct the image according to the target wavelet coefficients to obtain the denoised image corresponding to the initial image.

[0156] In some implementations, the processor 301, in the approximate estimation module process, executes:

[0157] A function determination module, used to determine a hyperbolic tangent function and adjustment parameters, and calculate a first function value corresponding to the initial wavelet coefficient under the hyperbolic tangent function;

[0158] A data comparison module is used to obtain an absolute value of the initial wavelet coefficient to obtain an absolute wavelet coefficient, and compare the absolute wavelet coefficient with the target wavelet threshold to obtain a comparison result;

[0159] A first processing module, configured to calculate a first difference between the absolute wavelet coefficient and the target wavelet threshold when the comparison result is that the absolute wavelet coefficient is greater than the target wavelet threshold, and calculate a first exponent value corresponding to the first difference under a natural exponent;

[0160] a ratio calculation module, used to calculate the ratio between the target wavelet threshold and the first exponent value to obtain a first ratio result;

[0161] A ratio adjustment module, used to adjust the first ratio result by using the adjustment parameter to obtain a second ratio result;

[0162] A first result module, configured to calculate the difference between the absolute wavelet coefficient and the second ratio result to obtain a third difference, and multiply the third difference by the first function value to obtain the target wavelet coefficient;

[0163] A second processing module, configured to calculate a second difference between the initial wavelet coefficient and the target wavelet threshold when the comparison result is that the absolute wavelet coefficient is less than or equal to the target wavelet threshold;

[0164] a difference adjustment module, configured to adjust the second difference using the adjustment parameter to obtain a fourth difference, and calculate a second exponent value corresponding to the fourth difference under a natural exponent;

[0165] The second result module is used to multiply the second exponent value and the first function value to obtain the target wavelet coefficient.

[0166] In some implementations, the processor 301 performs, during the image enhancement module process:

[0167] A window processing module, used to determine a target window and determine a window area corresponding to each target pixel in the denoised image under the target window;

[0168] A variance calculation module, used to perform variance calculation on the window area to obtain the window variance corresponding to the target pixel;

[0169] A weight calculation module, used to determine an adjustment factor corresponding to the target pixel in the denoised image according to the window variance, and determine a pixel weight corresponding to the target pixel according to the adjustment factor and the window variance;

[0170] A distribution calculation module, used to determine a target weight corresponding to an initial histogram corresponding to the denoised image according to the pixel weight, and determine a target histogram corresponding to the denoised image according to the target weight;

[0171] The contrast enhancement module is used to determine the corresponding cumulative distribution function according to the target histogram, and perform image enhancement processing on the denoised image according to the cumulative distribution function to obtain the target image.

[0172] In some implementations, the processor 301, in the distributed computing module process, executes:

[0173] A pixel acquisition module, used to determine a pixel range corresponding to the denoised image, and obtain any pixel value from the pixel range as a current pixel value;

[0174] A weight summing module, used for obtaining an associated weight corresponding to the current pixel value from the pixel weight, and summing the associated weights to obtain a first weight sum value corresponding to the current pixel value;

[0175] A weight processing module, used for obtaining the first weight sum value corresponding to each of the current pixel values ​​in the pixel range, and summing all the first weight sum values ​​to obtain a second weight sum value;

[0176] A result obtaining module, used for determining the target weight corresponding to the current pixel value according to the first weight sum value and the second weight sum value;

[0177] The target weight is obtained according to the following formula:

[0178]

[0179] Wherein, M represents the image length corresponding to the denoised image, N represents the image width corresponding to the denoised image, a1 and a2 represent adjustment parameters, var1(x,y) represents the normalized value of the window variance corresponding to the current pixel value when the horizontal position is x and the vertical coordinate is y in the denoised image, IF(img(x,y)=i,1,0) represents that the pixel value of the denoised image img when the horizontal position is x and the vertical coordinate is y is equal to the current pixel value i and takes 1, and the pixel value of the denoised image img when the horizontal position is x and the vertical coordinate is y is not equal to the current pixel value i and takes 0, m represents the lower limit value corresponding to the pixel range, n represents the upper limit value corresponding to the pixel range, var(x,y) represents the window variance corresponding to the current pixel value when the horizontal position is x and the vertical coordinate is y in the denoised image, max(var(x,y)) represents the maximum value corresponding to the window variance in the denoised image, and min(var(x,y)) represents the minimum value corresponding to the window variance in the denoised image.

[0180] In some implementations, the processor 301 further executes:

[0181] An image segmentation module, used to perform image segmentation on the target image to obtain a target area corresponding to the target image;

[0182] A region classification module is used to classify the target region using an image classification model to obtain a target classification result corresponding to the target region;

[0183] An image analysis module is used to perform reliability analysis on the target classification result to obtain the reliability of the target classification result;

[0184] A type determination module is used to determine the target type corresponding to the target area according to the reliability and the target classification result, so that the target doctor can diagnose and treat the target area according to the target type.

[0185] It should be noted that technicians in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working process of the terminal device described above can refer to the corresponding process in the aforementioned system embodiment for near-infrared second-zone fluorescence imaging optimization, and will not be repeated here.

[0186] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement any step of a system for optimizing near-infrared second-zone fluorescence imaging as provided in the description of the embodiment of the present invention.

[0187] The storage medium may be an internal storage unit of the terminal device described in the foregoing embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc., equipped on the terminal device.

[0188] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0189] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0190] The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A system for optimizing near-infrared second-zone fluorescence imaging, characterized in that: The system comprises: A data determination module, used to determine the fluorescent probe corresponding to the near-infrared region II and a target laser capable of emitting laser light in a wavelength band corresponding to the near-infrared region II; A data processing module, used for introducing the fluorescent probe into the target object, and using the target laser to excite the fluorescent probe in the target object, so that the fluorescent probe emits a fluorescent signal in the corresponding band of the near-infrared second region; A data acquisition module, used to collect the fluorescence signal using an imaging detector and convert the fluorescence signal into an initial image corresponding to the target object; The data optimization module is used to perform image processing on the initial image to obtain a target image corresponding to the target object.

2. The system according to claim 1, characterized in that The data optimization module comprises: An image processing module, used for performing image denoising on the initial image to obtain a denoised image corresponding to the initial image; The image enhancement module is used to perform image enhancement processing on the denoised image to obtain the target image corresponding to the denoised image.

3. The system according to claim 2, characterized in that The image processing module comprises: An image transformation module, used for performing wavelet transformation on the initial image to obtain initial wavelet coefficients corresponding to the initial image, and calculating the noise variance corresponding to the initial image according to the initial wavelet coefficients; A threshold calculation module, used to determine a target wavelet threshold according to the initial wavelet coefficient and the noise variance; An approximate estimation module, used to perform an approximate estimation on the initial wavelet coefficients using the target wavelet threshold to obtain target wavelet coefficients; The image denoising module is used to reconstruct the image according to the target wavelet coefficients to obtain the denoised image corresponding to the initial image.

4. The system according to claim 3, characterized in that The approximate estimation module comprises: A function determination module, used to determine a hyperbolic tangent function and adjustment parameters, and calculate a first function value corresponding to the initial wavelet coefficient under the hyperbolic tangent function; A data comparison module is used to obtain an absolute value of the initial wavelet coefficient to obtain an absolute wavelet coefficient, and compare the absolute wavelet coefficient with the target wavelet threshold to obtain a comparison result; A first processing module, configured to calculate a first difference between the absolute wavelet coefficient and the target wavelet threshold when the comparison result is that the absolute wavelet coefficient is greater than the target wavelet threshold, and calculate a first exponent value corresponding to the first difference under a natural exponent; a ratio calculation module, used to calculate the ratio between the target wavelet threshold and the first exponent value to obtain a first ratio result; A ratio adjustment module, used to adjust the first ratio result by using the adjustment parameter to obtain a second ratio result; A first result module, configured to calculate the difference between the absolute wavelet coefficient and the second ratio result to obtain a third difference, and multiply the third difference by the first function value to obtain the target wavelet coefficient; A second processing module, configured to calculate a second difference between the initial wavelet coefficient and the target wavelet threshold when the comparison result is that the absolute wavelet coefficient is less than or equal to the target wavelet threshold; a difference adjustment module, configured to adjust the second difference using the adjustment parameter to obtain a fourth difference, and calculate a second exponent value corresponding to the fourth difference under a natural exponent; The second result module is used to multiply the second exponent value and the first function value to obtain the target wavelet coefficient.

5. The system according to claim 2, characterized in that The image enhancement module comprises: A window processing module, used to determine a target window and determine a window area corresponding to each target pixel in the denoised image under the target window; A variance calculation module, used to perform variance calculation on the window area to obtain the window variance corresponding to the target pixel; A weight calculation module, used to determine an adjustment factor corresponding to the target pixel in the denoised image according to the window variance, and determine a pixel weight corresponding to the target pixel according to the adjustment factor and the window variance; A distribution calculation module, used to determine a target weight corresponding to an initial histogram corresponding to the denoised image according to the pixel weight, and determine a target histogram corresponding to the denoised image according to the target weight; The contrast enhancement module is used to determine the corresponding cumulative distribution function according to the target histogram, and perform image enhancement processing on the denoised image according to the cumulative distribution function to obtain the target image.

6. The system according to claim 5, characterized in that The distributed computing module comprises: A pixel acquisition module, used to determine a pixel range corresponding to the denoised image, and obtain any pixel value from the pixel range as a current pixel value; A weight summing module, used for obtaining an associated weight corresponding to the current pixel value from the pixel weight, and summing the associated weights to obtain a first weight sum value corresponding to the current pixel value; A weight processing module, used for obtaining the first weight sum value corresponding to each of the current pixel values ​​in the pixel range, and summing all the first weight sum values ​​to obtain a second weight sum value; A result obtaining module, used for determining the target weight corresponding to the current pixel value according to the first weight sum value and the second weight sum value; The target weight is obtained according to the following formula: Wherein, M represents the image length corresponding to the denoised image, N represents the image width corresponding to the denoised image, a1 and a2 represent adjustment parameters, var1(x,y) represents the normalized value of the window variance corresponding to the current pixel value when the horizontal position is x and the vertical coordinate is y in the denoised image, IF(img(x,y)=i,1,0) represents that the pixel value of the denoised image img when the horizontal position is x and the vertical coordinate is y is equal to the current pixel value i and takes 1, and the pixel value of the denoised image img when the horizontal position is x and the vertical coordinate is y is not equal to the current pixel value i and takes 0, m represents the lower limit value corresponding to the pixel range, n represents the upper limit value corresponding to the pixel range, var(x,y) represents the window variance corresponding to the current pixel value when the horizontal position is x and the vertical coordinate is y in the denoised image, max(var(x,y)) represents the maximum value corresponding to the window variance in the denoised image, and min(var(x,y)) represents the minimum value corresponding to the window variance in the denoised image.

7. The system according to claim 1, characterized in that The system further comprises: An image segmentation module, used to perform image segmentation on the target image to obtain a target area corresponding to the target image; A region classification module is used to classify the target region using an image classification model to obtain a target classification result corresponding to the target region; An image analysis module is used to perform reliability analysis on the target classification result to obtain the reliability of the target classification result; A type determination module is used to determine the target type corresponding to the target area according to the reliability and the target classification result, so that the target doctor can diagnose and treat the target area according to the target type.

8. A method for optimizing near-infrared second-zone fluorescence imaging, characterized in that: The method comprises: Determine the fluorescent probe corresponding to the second near-infrared region and the target laser capable of emitting the laser light in the corresponding wavelength band of the second near-infrared region; Introducing the fluorescent probe into a target object, and using the target laser to excite the fluorescent probe in the target object, so that the fluorescent probe emits a fluorescent signal in a wavelength band corresponding to the second near-infrared region; Using an imaging detector to collect the fluorescence signal, and converting the fluorescence signal into an initial image corresponding to the target object; The initial image is processed to obtain a target image corresponding to the target object.

9. A terminal device, characterized in that: The terminal device includes a processor and a memory; The memory is used to store computer programs; The processor is used to execute the computer program and implement the system for optimizing near-infrared second-zone fluorescence imaging according to any one of claims 1 to 7 when executing the computer program.

10. A computer storage medium for computer storage, characterized in that: The computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the system for optimizing near-infrared second-zone fluorescence imaging according to any one of claims 1 to 7.

Images