False fluorescence inhibition method and system of fluorescence endoscope camera system

Abstract

The invention discloses a false fluorescence suppression method and system for a fluorescence endoscope camera system, and the method comprises the steps: carrying out the denoising, binaryzation, threshold processing and nonlinear mapping pseudo-color processing of a fluorescence image, obtaining a false fluorescence threshold range, and enhancing the fluorescence image; obtaining a highlight region binary image of the visible light image according to the visible light image; obtaining a fusion weight map of the visible light image and the fluorescence image according to the false fluorescence threshold range and the highlight region binary image of the visible light image; and fusing the visible light image and the enhanced fluorescence image according to the fusion weight map to obtain a final enhanced fluorescence image. According to the method, false fluorescence interference can be inhibited, and the accuracy and distinction degree of pathological tissue development are enhanced.

Description

Technical Field

[0001] The invention relates to the field of image processing, and in particular to a false fluorescence suppression method and system for a fluorescent endoscope camera system. Background Art

[0002] The mechanism of action of the fluorescence endoscope camera system is to use special fluorescent dyes on patients, wait for the dyes to accumulate in the patient's malignant lesion area after metabolism, and then be excited by a laser of a specific wavelength, and the malignant tissue area corresponding to the fluorescent dye is electronically stained and developed. However, the fluorescent camera system generally has the problem of false fluorescence. The reason is that the filter of the camera system cannot completely filter out the reflected visible light and excitation light signals. When the observation distance is close or high-reflectivity tissues and metal instruments appear in the surgical field, the area where there is no accumulation of fluorescent dyes will also have a certain intensity of signal response during imaging, resulting in the electronic staining of normal tissues during imaging, which interferes with doctors' ability to distinguish the boundaries between normal tissues and malignant lesion tissues such as tumors and guide surgical resection.

[0003] In summary, there is an urgent need to provide a false fluorescence suppression method for a fluorescence endoscope camera system to suppress false fluorescence interference and enhance the accuracy and distinction of diseased tissue imaging. Summary of the invention

[0004] The object of the present invention is to provide a false fluorescence suppression method and system for a fluorescence endoscope camera system, so as to suppress the interference of false fluorescence and enhance the accuracy and differentiation of diseased tissue imaging.

[0005] In order to solve the above technical problems, the present invention provides a technical solution: a false fluorescence suppression method of a fluorescent endoscope camera system, comprising:

[0006] S1, obtaining an original visible light image and an original fluorescence image of a fluorescence endoscope system;

[0007] S2, removing discrete noise points of the original fluorescence image to obtain a first enhanced fluorescence image;

[0008] S3, calculating a false fluorescence threshold range according to a histogram of the first enhanced fluorescence image;

[0009] S4, performing threshold processing on the first enhanced fluorescence image according to the false fluorescence threshold range to obtain a second enhanced fluorescence image;

[0010] S5, performing nonlinear mapping on the pixels of the second enhanced fluorescence image, and then obtaining a third enhanced fluorescence image through pseudo color processing;

[0011] S6, generating a highlight region binary image of the original visible light image according to the brightness value, saturation value, and local region texture intensity value of the pixels of the original visible light image;

[0012] S7, generating a fusion weight map of the original visible light image and the original fluorescence image according to the false fluorescence threshold range and the highlight region binarization map of the original visible light image;

[0013] S8. Perform image fusion on the original visible light image and the third enhanced fluorescence image according to the fusion weight map to obtain a final enhanced fluorescence image.

[0014] According to the above scheme, step S2 includes: applying a radius filter to remove discrete noise points of the original fluorescence image.

[0015] According to the above scheme, step S3 includes:

[0016] S301, calculating the cumulative probability distribution of the histogram of the first enhanced fluorescence image;

[0017] S302: Obtain the first quartile q of the histogram of the first enhanced fluorescence image according to the cumulative probability distribution of the histogram of the first enhanced fluorescence image. 1 , the second quartile q 2 and the third quartile q 3 ;

[0018] S303, according to the segmentation threshold t, the fluorescence image is divided into a true fluorescence area and a false fluorescence area, and the inter-class variance between the pixels in the true fluorescence area and the pixels in the false fluorescence area is calculated by Otsu threshold method; t satisfies q 1 <t<q 3 ;

[0019] S304, obtaining a first fluorescence threshold according to the segmentation threshold that can obtain the maximum inter-class variance and the second quartile; and converting the third quartile q 3 Set as the second fluorescence threshold.

[0020] According to the above scheme, step S6 includes:

[0021] S601, converting the original visible light image from the RGB color space to the HSV color space, and extracting the brightness value and saturation value of the pixels in the original visible light image;

[0022] S602, traversing the brightness values, and calculating the texture intensity values ​​of the local areas of the pixels of the original visible light image;

[0023] S603, binarizing the brightness value according to the brightness value, the saturation value, and the texture intensity value of the local area, dividing the pixels of the original visible light image into a highlight area and a non-highlight area, thereby obtaining a preliminary highlight area binary image of the original visible light image;

[0024] S603 , dilate the preliminary highlight region binary image to obtain a highlight region binary image.

[0025] According to the above scheme, step S602 includes:

[0026] S6021, calculating the minimum pixel value and the maximum pixel value of the local area where the pixels of the original visible light image are located;

[0027] S6022, obtaining the gray level co-occurrence matrix of the local area at the specified direction and distance;

[0028] S6023, normalizing the elements of the gray level co-occurrence matrix of the local area;

[0029] S6024. Calculate the texture intensity value of the local area based on the elements of the normalized gray level co-occurrence matrix.

[0030] According to the above scheme, step S6024 includes:

[0031] The texture intensity value of the local area is determined according to the minimum and maximum values ​​of the pixels in the local area and the elements of the normalized gray level co-occurrence matrix.

[0032] According to the above scheme, step S4 includes:

[0033] The pixels of the first enhanced fluorescence image are traversed, and the pixels whose pixel values ​​are less than the first fluorescence threshold and greater than the second fluorescence threshold are set as false fluorescence pixels, thereby obtaining the second enhanced fluorescence image.

[0034] According to the above scheme, step S5 includes:

[0035] S501, obtaining histogram statistics of the second enhanced fluorescence image;

[0036] Calculating the maximum value, the minimum value and the average value of the histogram statistics of the second enhanced fluorescence image and calculating the gamma value of the nonlinear gamma curve;

[0037] S502, normalizing the pixels of the second enhanced fluorescence image, and then applying a gamma value to perform nonlinear mapping;

[0038] S503 , performing pseudo-color processing on the second enhanced fluorescence image after nonlinear mapping based on the image pixel intensity and the specified pseudo-color color coordinate value to obtain a third enhanced fluorescence image.

[0039] According to the above scheme, step S7 includes:

[0040] A first fusion weight map is generated according to the first fluorescence threshold and the second fluorescence threshold, a second fusion weight map is generated by traversing the highlight area binary map of the original visible light image, and a fusion weight map is generated based on the first fusion weight map and the second fusion weight map.

[0041] The present invention also provides a fluorescent endoscope camera system, comprising:

[0042] An image acquisition module, used for acquiring an original visible light image and an original fluorescence image of a fluorescence endoscope system;

[0043] A first image enhancement module, used to remove discrete noise points of the original fluorescence image to obtain a first enhanced fluorescence image;

[0044] A first calculation module, used for calculating a false fluorescence threshold range according to a histogram of the first enhanced fluorescence image;

[0045] A second image enhancement module is used to perform threshold processing on the first enhanced fluorescence image according to the false fluorescence threshold range to obtain a second enhanced fluorescence image;

[0046] A third image enhancement module, used for performing nonlinear mapping on pixels of the second enhanced fluorescence image, and then obtaining a third enhanced fluorescence image by pseudo-color processing;

[0047] A highlight region calculation module is used to generate a highlight region binary image of the original visible light image according to the brightness value, saturation value, and local region texture intensity value of the pixels of the original visible light image;

[0048] A fusion weight map calculation module is used to generate a fusion weight map of the original visible light image and the original fluorescence image according to the false fluorescence threshold range and the highlight area binarization map of the original visible light image;

[0049] The image fusion module is used to fuse the original visible light image and the third enhanced fluorescence image according to the fusion weight map to obtain a final enhanced fluorescence image.

[0050] The present invention also provides a false fluorescence suppression device for a fluorescence endoscope camera system, and the device executes the false fluorescence suppression method for a fluorescence endoscope camera system as described above.

[0051] The beneficial effects of the present invention are as follows: the present invention performs filtering and denoising on the original fluorescence image, and then uses the histogram of the denoised fluorescence image to perform false fluorescence threshold processing, which can effectively suppress the false fluorescence interference caused by the background noise and infrared excitation light in the fluorescence image, and realize the preliminary enhancement of the original fluorescence image. Then, by performing nonlinear mapping, pseudo-color processing and image fusion on the pixels of the fluorescence image after preliminary enhancement, the contrast, layering and boundary distinction of the fluorescence image can be significantly enhanced, and the fluorescence image can be enhanced again. Based on the brightness, saturation and edge intensity information of the visible light image pixels, a binary map of the highlight area is obtained, and the characteristic that the false fluorescence caused by visible light usually appears in the fluorescence image area corresponding to the highlight of the visible light image is used. According to the highlight binary map, a fusion weight map of the visible light image and the fluorescence image is generated, and finally the enhanced fluorescence image is fused with the visible light image according to the fusion weight map, which can accurately suppress the false fluorescence interference caused by the visible light image. The method is suitable for medical equipment such as fluorescence microscopes / endoscopes, and helps to improve the accuracy of diagnosis.

[0052] Furthermore, by removing discrete noise points through the radius filter, the clarity and quality of the fluorescence image can be significantly improved, the random noise in the image can be reduced, and the subsequent processing steps can be more precise. The noise-free image is easier to perform further image analysis and processing, such as threshold determination and false fluorescence suppression, thereby improving the diagnostic value of the final image.

[0053] Furthermore, by calculating the texture intensity value of the local area, the highlight area in the image can be identified more accurately, which helps to distinguish different features in the image (such as tissue type or lesion area), and the accurate calculation of the texture intensity value helps to generate a high-quality highlight area binary image, and then in the image fusion process, the information of the visible light image and the fluorescence image can be more effectively combined to improve the diagnostic accuracy of the final image. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a flow chart of a false fluorescence suppression method of a fluorescence endoscope camera system according to Embodiment 1 of the present invention;

[0055] Figure 2 1 is a schematic structural diagram of a false fluorescence suppression device of a fluorescence endoscope camera system according to a second embodiment of the present invention;

[0056] Figure 3 It is a schematic diagram of the structure of an electronic device according to the third embodiment of the present invention.

[0057] In the figure: 20-image acquisition module, 21-first processing module, 22-first calculation module, 23-second calculation module, 24-third calculation module, 25-fourth calculation module, 26-second processing module, 27-third processing module, 28-fourth processing module, 30-electronic device, 31-processor, 32-memory. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings of the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0059] Embodiment 1:

[0060] This embodiment provides a method for suppressing false fluorescence in a fluorescent endoscope camera system. The specific process is as follows: Figure 1 As shown, the technical solution includes the following steps:

[0061] S1: Acquire the original visible light image and fluorescence image of the fluorescence endoscope system; this step can effectively suppress the background noise in the fluorescence image and achieve preliminary enhancement of the original fluorescence image;

[0062] S2: applying a radius filter to the original fluorescence image to remove discrete noise points to obtain a first enhanced fluorescence image;

[0063] S3: calculating the first and second fluorescence thresholds according to the histogram of the first enhanced fluorescence image and the Otsu threshold algorithm;

[0064] S4: generating a binarized image of a highlight region of the visible light image according to the brightness, saturation and edge strength of the pixels of the visible light image (using the characteristic that false fluorescence caused by visible light usually appears in the fluorescent image region corresponding to the highlight of the visible light image);

[0065] S5: performing threshold processing on the first enhanced fluorescence image according to the first and second fluorescence thresholds to obtain a second enhanced fluorescence image; this step can effectively suppress false fluorescence interference caused by infrared excitation light and realize further enhancement of the original fluorescence image;

[0066] S6: performing nonlinear mapping on the pixels of the second enhanced fluorescence image to enhance the contrast of the fluorescence signal, and then obtaining a third enhanced fluorescence image through pseudo-color processing; this step can significantly enhance the contrast, layering and boundary distinction of the fluorescence image, thereby achieving further enhancement of the fluorescence image;

[0067] S7: generating a visible light image and fluorescence image fusion weight map according to the first and second fluorescence thresholds and the highlight region binarization map of the visible light image;

[0068] S8: performing image fusion on the visible light image and the third enhanced fluorescence image according to the fusion weight map to obtain a final enhanced fluorescence image with false fluorescence suppressed; this step accurately suppresses false fluorescence interference caused by the visible light image.

[0069] Further, in some of the embodiments, the filter radius parameter of the radius filter in step S2 is set as follows:

[0070] r=max(imH,imW)×ratio0

[0071] Among them, r is the filter radius, imH and imW are the height and width of the fluorescence image respectively, and ratio0 is used to control the radius of the filter window. 0 The formula for the output value p′ of any pixel point p after passing through the radius filter is as follows:

[0072]

[0073] Among them, p i is the pixel within the filter window with center p and radius r respectively, t 3 is the filtering threshold, cnt is a pixel counter, which counts the number of pixels in the original fluorescence image within the filtering window that are less than t 3 The number of pixels, ratio1 is used to control the pixel number threshold.

[0074] In some specific implementations, ratio0 can be set to 1 / 128, ratio1 can be set to 0.6, t 3 Can be set to 16.

[0075] Further, in some embodiments, the above step S3 of determining the first fluorescence threshold and the second fluorescence threshold comprises the following steps:

[0076] S31: Acquire histogram statistics of the first enhanced fluorescence image;

[0077] S32: calculating a histogram cumulative probability distribution according to the histogram statistical data of the first enhanced fluorescence image;

[0078] S33: Obtain the first quartile q of the histogram according to the cumulative probability distribution 1 , the second quartile q 2 and the third quartile q 3 ;

[0079] S34: For any segmentation threshold q 1 <t<q 3 , the fluorescence image is divided into true fluorescence area and false fluorescence area, and the inter-class variance of pixels in the two types of areas is calculated by Otsu threshold method;

[0080] S35: Obtain the first fluorescence threshold value, q, according to the segmentation threshold value corresponding to the maximum inter-class variance and the second quartile. 3 is the second fluorescence threshold;

[0081] Furthermore, in the above step S34, the first fluorescence threshold is the minimum value of the segmentation threshold determined by the maximum inter-class variance and the second quartile, and the second fluorescence threshold is the third quartile q 3 ;

[0082] Furthermore, in some of the embodiments, the calculation steps of the highlight region binary image of the visible light image in step S4 are as follows:

[0083] S41: converting the original visible light image from the RGB color space to the HSV color space, and extracting the brightness component and the saturation component of the visible light image;

[0084] S42: traversing the brightness components to calculate the texture intensity value of the local area of ​​the pixel;

[0085] S43: Binarizing the brightness component according to the brightness value and saturation value of the pixel and the texture intensity of the local area of ​​the pixel, dividing the pixel into a highlight area and a non-highlight area, and thereby obtaining a first highlight area binary image of the visible light image;

[0086] S44: performing morphological dilation processing on the first highlight region binary image to obtain a final highlight region binary image;

[0087] Furthermore, the calculation formulas for the brightness value and saturation value of the visible light image pixel in the above step S41 are as follows:

[0088] v=max(r,g,b)

[0089]

[0090] Among them, v is the brightness value of the pixel and s is the saturation value of the pixel.

[0091] Furthermore, the calculation of the texture intensity of the local area of ​​the visible light image pixel in the above step S42 includes the following steps:

[0092] S421: Calculate the minimum and maximum values ​​of pixels in the local area where the pixel is located;

[0093] S422: Obtaining the gray level co-occurrence matrix of the local area at a specified direction and distance;

[0094] S423: Normalizing the elements of the gray level co-occurrence matrix of the local area;

[0095] S424: Calculating the texture intensity of the local area based on the elements of the normalized gray level co-occurrence matrix;

[0096] Further, in some specific embodiments, the local area in the above step S421 is centered on the pixel, and the size of the local area can be set to 8, 16, 32, etc.;

[0097] Further, in some specific embodiments, the direction of the gray level co-occurrence matrix in the above step S422 is set to 0°, 45°, 90° or 135°, etc., and the distance is set to 1;

[0098] Furthermore, the number of rows and columns of the gray level co-occurrence matrix in the above step S422 is determined by the minimum value and the maximum value calculated in step S431, that is, the number of rows and the number of columns are equal to the number of pixel levels between the minimum value and the maximum value;

[0099] Furthermore, in step S423, each element of the gray level co-occurrence matrix is ​​normalized by dividing it by the sum of all elements;

[0100] Furthermore, the formula for calculating the texture intensity of the local area in the above step S424 based on the normalized gray level co-occurrence matrix elements is as follows:

[0101]

[0102] Where e is the texture intensity value of the pixel, minP and maxP are the minimum and maximum values ​​of the local area respectively, and M i,j is the element in the i-th row and j-th column of the normalized gray-level co-occurrence matrix;

[0103] In addition, in some other implementations, the texture intensity value of the pixel may also adopt other image texture edge operators such as gradient operator, Robert operator, sobel operator, Prewitt operator, etc.;

[0104] Furthermore, the formula for generating the first highlight region binary image of the visible light image in step S43 is as follows:

[0105]

[0106] Among them, B i is a binary graph with only 0 and 1 elements, v i 、s i and e iare the brightness, saturation and texture intensity values ​​of the pixel, v thr 、s thr and e thr They are the brightness threshold, saturation threshold, and texture intensity threshold of the pixel;

[0107] Furthermore, in some specific embodiments, the brightness threshold, saturation threshold and texture intensity threshold have a normalized range of 0-1, and the value is v thr =0.72, s thr = 0.24 and e thr =0.16.

[0108] Furthermore, the step S5 traverses the first enhanced fluorescence image, locates pixels with pixel values ​​less than the first fluorescence threshold and greater than the second fluorescence threshold as false fluorescence pixels, sets them to 0, and obtains the second enhanced fluorescence image after threshold processing;

[0109] Further, in some embodiments, the step S6 of enhancing the fluorescence signal contrast comprises the following steps:

[0110] S61: Acquire histogram statistics of the second enhanced fluorescence image;

[0111] S62: Calculating a maximum value maxP, a minimum value minP and an average value meanP of the second enhanced fluorescence image according to the histogram;

[0112] S63: Calculate the gamma parameter of the nonlinear gamma curve according to the maximum value maxP, the minimum value minP and the average value meanP, and the calculation formula is as follows:

[0113]

[0114] S64: normalizing the pixels of the second enhanced fluorescence image, and then applying the gamma value to perform nonlinear mapping, the calculation formula is as follows:

[0115]

[0116] Among them, p and p″ are the pixels before and after nonlinear mapping, respectively, and clip limits the pixels after mapping to the specified interval [minP, 255].

[0117] S65: performing pseudo-color processing on the fluorescence image enhanced by the nonlinear mapping based on the image pixel intensity and the specified pseudo-color color coordinate value to obtain a third enhanced fluorescence image;

[0118] Furthermore, in some of the embodiments, the step S7 generates a first fusion weight map according to the first fluorescence threshold and the second fluorescence threshold, traverses the final highlight area binary map to generate a second fusion weight map, and generates a final fusion weight map W based on the first fusion weight map and the second fusion weight map, that is, the weight values ​​of pixels in the fluorescence image that are less than the first fluorescence threshold and greater than the second fluorescence threshold are set to 0, and the weight of the visible light pixel corresponding to the position of 1 in the binary map is set to 1.

[0119] Furthermore, in some embodiments, the enhanced fluorescence image F in step S8 4 The calculation formula is as follows:

[0120] F′=I×(1-W)+F×W

[0121] Wherein, I is the visible light image, F and F′ are the third enhanced fluorescence image and the final enhanced fluorescence image respectively, and W is the final fusion weight map;

[0122] Embodiment 2:

[0123] Reference Figure 2 This embodiment provides a false fluorescence suppression device for a fluorescence endoscope camera system, comprising:

[0124] An image acquisition module 20, used to acquire an original visible light image and an original fluorescence image of a fluorescence endoscope system;

[0125] A first processing module 21, used to remove discrete noise points of the fluorescence image to obtain a first enhanced fluorescence image;

[0126] A first calculation module 22, used for calculating the first and second fluorescence thresholds of the first enhanced fluorescence image;

[0127] A second calculation module 23, used to generate a binary image of a highlight area of ​​a visible light image;

[0128] A third calculation module 24, used to generate a fusion weight map of the visible light image and the fluorescence image;

[0129] A fourth calculation module 25, used for calculating the gamma value of the nonlinear mapping of the enhanced fluorescence image and performing pseudo color processing;

[0130] A second processing module 26, configured to perform threshold processing on the fluorescence image according to the first fluorescence threshold and the second fluorescence threshold;

[0131] A third processing module 27, configured to perform nonlinear mapping enhancement on the fluorescence image according to the gamma value;

[0132] A fourth processing module 28, configured to perform image fusion on the visible light image and the fluorescence image according to the fusion weight map to generate a final fused image after suppressing false fluorescence;

[0133] Embodiment three:

[0134] This embodiment also provides an optional electronic device 30, the structural diagram of which is shown in FIG. Figure 3 , including a processor 31 and a memory 32, the memory 32 stores computer programs and instructions, and when the processor 31 executes the computer program and instructions, any step of the false fluorescence suppression method of the fluorescence endoscope camera system of embodiment 1 is executed.

[0135] The memory 32 in this embodiment can be any type of volatile and non-volatile memory or any combination thereof, and the non-volatile memory is a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic memory, a flash memory, a magnetic disk or an optical disk. The volatile memory can be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct RAM bus random access memory (DRRAM). The memory 32 of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.

[0136] Embodiment 4:

[0137] This embodiment provides a computer-readable storage medium, on which a computer program or executable instructions are stored. When the computer program or instructions are executed by one or more processors, any step of the false fluorescence suppression method of the fluorescence endoscope camera system of the first embodiment is executed.

[0138] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0139] In addition, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0140] In addition, all functional modules in the embodiments of the present application may be integrated into one processing unit, or each module may be a separate unit, or two or more modules may be integrated into one unit; the above-mentioned integrated modules may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0141] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for suppressing false fluorescence in a fluorescence endoscope camera system, characterized in that: include: S1, obtaining an original visible light image and an original fluorescence image of a fluorescence endoscope system; S2, removing discrete noise points of the original fluorescence image to obtain a first enhanced fluorescence image; S3, calculating a false fluorescence threshold range according to a histogram of the first enhanced fluorescence image; S4, performing threshold processing on the first enhanced fluorescence image according to the false fluorescence threshold range to obtain a second enhanced fluorescence image; S5, performing nonlinear mapping on the pixels of the second enhanced fluorescence image, and then obtaining a third enhanced fluorescence image through pseudo color processing; S6, generating a highlight region binary image of the original visible light image according to the brightness value, saturation value, and local region texture intensity value of the pixels of the original visible light image; S7, generating a fusion weight map of the original visible light image and the original fluorescence image according to the false fluorescence threshold range and the highlight region binarization map of the original visible light image; S8. Perform image fusion on the original visible light image and the third enhanced fluorescence image according to the fusion weight map to obtain a final enhanced fluorescence image.

2. The false fluorescence suppression method of the fluorescence endoscope camera system according to claim 1, characterized in that: Step S2 includes: applying a radius filter to remove discrete noise points of the original fluorescence image.

3. The false fluorescence suppression method of the fluorescence endoscope camera system according to claim 1, characterized in that: Step S3 includes: S301, calculating the cumulative probability distribution of the histogram of the first enhanced fluorescence image; S302, obtaining a first quartile q1, a second quartile q2, and a third quartile q3 of the histogram of the first enhanced fluorescence image according to the cumulative probability distribution of the histogram of the first enhanced fluorescence image; S303, according to the segmentation threshold t, the fluorescence image is divided into a true fluorescence area and a false fluorescence area, and the inter-class variance between the pixels in the true fluorescence area and the pixels in the false fluorescence area is calculated by Otsu threshold method; t satisfies q1 <t<q3; S304 , obtaining a first fluorescence threshold according to the segmentation threshold that can obtain the maximum inter-class variance and the second quartile; and setting the third quartile q3 as the second fluorescence threshold.

4. The false fluorescence suppression method of the fluorescence endoscope camera system according to claim 1, characterized in that: Step S6 includes: S601, converting the original visible light image from the RGB color space to the HSV color space, and extracting the brightness value and saturation value of the pixels in the original visible light image; S602, traversing the brightness values, and calculating the texture intensity values ​​of the local areas of the pixels of the original visible light image; S603, binarizing the brightness value according to the brightness value, the saturation value, and the texture intensity value of the local area, dividing the pixels of the original visible light image into a highlight area and a non-highlight area, thereby obtaining a preliminary highlight area binary image of the original visible light image; S603 , dilate the preliminary highlight region binary image to obtain a highlight region binary image.

5. The false fluorescence suppression method of the fluorescence endoscope camera system according to claim 4, characterized in that: Step S602 includes: S6021, calculating the minimum pixel value and the maximum pixel value of the local area where the pixels of the original visible light image are located; S6022, obtaining the gray level co-occurrence matrix of the local area at the specified direction and distance; S6023, normalizing the elements of the gray level co-occurrence matrix of the local area; S6024. Calculate the texture intensity value of the local area based on the elements of the normalized gray level co-occurrence matrix.

6. The false fluorescence suppression method of the fluorescence endoscope camera system according to claim 5, characterized in that: Step S6024 includes: The texture intensity value of the local area is determined according to the minimum and maximum values ​​of the pixels in the local area and the elements of the normalized gray level co-occurrence matrix.

7. The false fluorescence suppression method of a fluorescence endoscope camera system according to claim 1, characterized in that: Step S4 includes: The pixels of the first enhanced fluorescence image are traversed, and the pixels whose pixel values ​​are less than the first fluorescence threshold and greater than the second fluorescence threshold are set as false fluorescence pixels, thereby obtaining the second enhanced fluorescence image.

8. The false fluorescence suppression method of a fluorescence endoscope camera system according to claim 1, characterized in that: Step S5 includes: S501, obtaining histogram statistics of the second enhanced fluorescence image; Calculating the maximum value, the minimum value and the average value of the histogram statistics of the second enhanced fluorescence image and calculating the gamma value of the nonlinear gamma curve; S502, normalizing the pixels of the second enhanced fluorescence image, and then applying a gamma value to perform nonlinear mapping; S503 , performing pseudo-color processing on the second enhanced fluorescence image after nonlinear mapping based on the image pixel intensity and the specified pseudo-color color coordinate value to obtain a third enhanced fluorescence image.

9. The false fluorescence suppression method of a fluorescence endoscope camera system according to claim 1, characterized in that: Step S7 includes: A first fusion weight map is generated according to the first fluorescence threshold and the second fluorescence threshold, a second fusion weight map is generated by traversing the highlight area binary map of the original visible light image, and a fusion weight map is generated based on the first fusion weight map and the second fusion weight map.

10. A fluorescent endoscope camera system, characterized in that: include: An image acquisition module, used for acquiring an original visible light image and an original fluorescence image of a fluorescence endoscope system; A first image enhancement module, used to remove discrete noise points of the original fluorescence image to obtain a first enhanced fluorescence image; A first calculation module, used for calculating a false fluorescence threshold range according to a histogram of the first enhanced fluorescence image; A second image enhancement module is used to perform threshold processing on the first enhanced fluorescence image according to the false fluorescence threshold range to obtain a second enhanced fluorescence image; A third image enhancement module, used for performing nonlinear mapping on pixels of the second enhanced fluorescence image, and then obtaining a third enhanced fluorescence image by pseudo-color processing; A highlight region calculation module is used to generate a highlight region binary image of the original visible light image according to the brightness value, saturation value, and local region texture intensity value of the pixels of the original visible light image; A fusion weight map calculation module is used to generate a fusion weight map of the original visible light image and the original fluorescence image according to the false fluorescence threshold range and the highlight area binarization map of the original visible light image; The image fusion module is used to fuse the original visible light image and the third enhanced fluorescence image according to the fusion weight map to obtain a final enhanced fluorescence image.

Images