Fluorescence imaging system based on exterior mirror

Abstract

The invention relates to the technical field of fluorescence imaging diagnosis, and discloses a fluorescence imaging system based on an exterior mirror, and the system specifically comprises a to-be-processed region obtaining module which is used for extracting a high-brightness region of a fluorescence imaging image through an image segmentation method, carrying out the merging operation, and determining a to-be-processed region; the signal generation module is used for identifying and analyzing the to-be-processed region and generating an analysis signal; the key area coincidence judgment module is used for identifying whether the to-be-processed area is a key area or not based on the analysis signal and generating a pre-optimization signal; and the change analysis module is used for acquiring a key non-overlapping region based on the pre-optimized signal. According to the method, the problem that diagnosis is interfered by local overbrightness of the imaging image is solved to a certain extent, the image quality is improved, the misdiagnosis and missed diagnosis probability is reduced, whether the local overbrightness position affects diagnosis or not is analyzed, the accuracy, reliability and overall efficiency of fluorescence imaging diagnosis are improved, and powerful support is provided for clinical diagnosis.

Description

Technical Field

[0001] The present invention relates to the technical field of fluorescence imaging diagnosis, and particularly to a fluorescence imaging system based on an exoscope. Background Art

[0002] With fluorescence imaging technology as the core and an exoscope as the imaging carrier, through specific optical and electronic components, the acquisition, processing, and display of fluorescence signals in the target area are realized. Compared with traditional endoscope imaging, the exoscope does not need to be directly inserted into the human body, but observes the target area from outside the body, reducing the invasiveness to patients and improving the safety and convenience of operation; However, in the imaging process of the exoscope fluorescence imaging system, due to improper setting of imaging device parameters and other reasons, the situation of local over-brightness in the image often occurs, which further interferes with the accurate observation and analysis of the condition, making it difficult to effectively process and interpret the information in the high-brightness area, increasing the complexity of subsequent diagnosis, and thus prone to misdiagnosis or missed diagnosis in the diagnosis process, affecting the accuracy and reliability of fluorescence imaging diagnosis. Summary of the Invention

[0003] The purpose of the present invention is to provide a fluorescence imaging system based on an exoscope to solve at least one of the above-mentioned prior art problems.

[0004] The present invention provides a fluorescence imaging system based on an exoscope, which specifically includes: A to-be-processed area acquisition module: extracting the high-brightness area of the fluorescence imaging image through an image segmentation method and performing a merging operation to determine the to-be-processed area; A signal generation module: identifying and analyzing the to-be-processed area to generate an analysis signal; A key area coincidence determination module: based on the analysis signal, identifying whether the to-be-processed area is a key area and generating a pre-optimization signal; A change analysis module: based on the pre-optimization signal, obtaining the key non-coincidence area, performing a change analysis on the pixel values to obtain the influencing pixel points, and identifying whether it will affect the diagnosis result.

[0005] Advantages of the Present Invention 1. The present invention determines the area to be processed by acquiring and merging high-brightness areas, reducing interference and providing clear data for subsequent analysis. Then, by comparing the area to be processed with the fluorescence map, and according to the determination result, it decides whether to optimize the image or perform the next analysis, enhancing the image's ability to present lesion features, enabling doctors to observe the details of the lesion more clearly and accurately, providing a more powerful image basis for diagnosis. By analyzing the change in pixel values of the key non-overlapping areas to evaluate the impact on diagnosis, if there is an impact, the device parameters are optimized, thereby increasing the accuracy of diagnosis and reducing misdiagnosis or missed diagnosis caused by local over-bright imaging. 2. To a certain extent, the present invention solves the problem of local over-bright imaging interfering with diagnosis, improves the image quality, reduces the probability of misdiagnosis and missed diagnosis, and analyzes whether the local over-bright position affects the diagnosis, enhancing the accuracy, reliability, and overall efficiency of fluorescence imaging diagnosis, providing strong support for clinical diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0007] Figure 1 It is a schematic structural diagram of the fluorescence imaging system based on an external endoscope of the present invention; Figure 2 It is a flowchart of the fluorescence imaging method based on an external endoscope of the present invention; Figure 3 It is a schematic structural diagram of the fluorescence imaging device based on an external endoscope of the present invention.

[0008] In the figure: 3. Computer device; 301. Processor; 302. Memory; 303. Computer program; DETAILED DESCRIPTION OF THE EMBODIMENTS

[0009] In order to enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention. Embodiment 1

[0010] Figure 1The flowchart of the fluorescence imaging system based on an external endoscope provided by Embodiment 1 of the present invention is applicable to the situation where the imaging image has local overbrightness. The fluorescence imaging system based on an external endoscope can be implemented by software and / or hardware, and can be configured in a fluorescence imaging device based on an external endoscope. Optionally, the fluorescence imaging device based on an external endoscope can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc. The embodiments of the present invention do not limit this.

[0011] The fluorescence imaging system based on an external endoscope provided by the embodiments of the present invention specifically includes: A module for obtaining the area to be processed: Obtain a fluorescence imaging image, monitor the imaging image through brightness histogram analysis and in combination with an image segmentation method, obtain high-brightness areas, and perform a merging operation to determine the area to be processed; Among them, the image segmentation method includes: a region growing algorithm; In some embodiments, use an external endoscope device to capture a fluorescence imaging image of a target area, and preprocess the fluorescence imaging image to obtain pixel values; Among them, preprocessing the fluorescence imaging image includes converting the image into a grayscale image and image filtering. The specific process is as follows: Use the weighted average method to obtain the image grayscale value Gray. Among them, the calculation formula for the image grayscale value Gray is: , where R, G, and B are the values of the red, green, and blue channels respectively; Determine the size and standard deviation of the Gaussian filter. According to the filter size and standard deviation, generate a two-dimensional Gaussian filter template according to the Gaussian function , where is the coordinate of the central pixel, is the center position of the filter, x and y are the coordinate offsets relative to the central pixel, is the standard deviation of the Gaussian filter; Slide the generated Gaussian filter template on the image, starting from the upper left corner of the image, moving one pixel each time until the entire image is traversed. For each image pixel area covered by the template, multiply each element in the template by the corresponding image pixel value, and then add these products to obtain the filtered pixel value; Converting the image into a grayscale image is to reduce the amount of data, improve the subsequent processing efficiency, and at the same time highlight the brightness information of the image, which is beneficial to obtaining high-brightness areas through brightness histogram analysis and region growing algorithm later. Image filtering is to make the image smoother. By performing weighted averaging on neighboring pixels, the main structure of the image can be retained while reducing the influence of noise, thereby providing more reliable data for subsequent brightness histogram analysis and region growing algorithm; Calculate the luminance histogram based on the obtained pixel values. The abscissa represents the pixel values (usually in the range of 0 - 255, corresponding to black to white), and the ordinate is the number of pixels corresponding to each pixel value. By traversing each pixel in the image, count the number of pixels with different pixel values to construct the luminance histogram; Set a high luminance threshold, which is set by those skilled in the art based on a large amount of historical experimental data and experience; Compare the pixel value with the high luminance threshold. If the pixel value is greater than the high luminance threshold, mark it as a high luminance pixel point; if the pixel value is less than or equal to the high luminance threshold, mark it as a normal pixel point; Based on all high luminance pixel points, use the high luminance pixel points as seed points respectively; Starting from the seed points, traverse the neighborhood pixel points of the seed points in the set order; Among them, the set order includes: centered on the seed points, in a clockwise or counterclockwise direction, or in the order from left to right, from top to bottom; Based on the pixel values of each neighborhood pixel point, identify whether the pixel value is within the pixel similarity interval. If the pixel value is within the similarity interval, mark the corresponding pixel point as a mergeable pixel point; otherwise, mark the corresponding pixel point as a non - mergeable pixel point; Among them, the pixel similarity interval is [XSY, XSZ], XSZ is the maximum value among all high luminance pixel points, XSY is the difference between the high luminance threshold and the luminance step size, and the luminance step size is set by those skilled in the art according to experience; Based on the mergeable pixels, use them as new seed points, traverse the neighborhood pixel points of the seed points, and repeat the process of identifying mergeable pixel points until no more mergeable pixel points appear. Obtain all mergeable pixel points and mark the positions where the mergeable pixel points are located as high luminance regions; Obtain all high luminance regions, based on any two high luminance regions; Respectively traverse the pixel coordinates of the two high luminance regions, count the number of pixel points that belong to both high luminance regions, and mark it as the number of overlapping pixel points; Identify the number of pixel points in the two high luminance regions and compare them, and extract the high luminance region with fewer pixel points; Perform a ratio process on the number of overlapping pixel points and the number of pixel points in the high luminance region with fewer pixel points to obtain the overlapping ratio; Respectively calculate the centroid coordinates of the two high luminance regions and calculate the distance value between the two centroid coordinates; Among them, the centroid coordinate is the average value of all pixel coordinates within the high luminance region, and the distance value is calculated using the Euclidean distance formula; The distance value is processed by taking the ratio with the distance standard value to obtain a distance ratio. Here, the distance standard value can be summarized and set according to the size of the fluorescence imaging image; It should be noted that if the distance value is zero, the corresponding two highlighted regions are directly merged; The overlapping occupancy ratio and the distance ratio are calculated by taking the ratio to obtain a merging coefficient; It should be explained that the merging coefficient is calculated from the overlapping occupancy ratio and the distance ratio. Among them, the larger the overlapping occupancy ratio, the larger the overlapping region of the two high-brightness regions. The smaller the distance ratio, the closer the two high-brightness regions are in space. Therefore, the larger the merging coefficient, the more likely the two high-brightness regions can be merged; The function of calculating the merging coefficient is as follows: Firstly, comprehensively considering the overlapping degree and the spatial distance can more comprehensively and accurately judge whether these two regions are suitable for merging. Secondly, it helps to accurately divide the regions to be processed, thereby reducing the impact of the excessive fragmentation of high-brightness regions on the complexity of subsequent analysis; The merging coefficient is compared with the merging coefficient threshold. Here, the merging coefficient threshold is determined by those skilled in the art based on a large amount of experimental data and experience summary; If the merging coefficient is greater than the merging coefficient threshold, the corresponding two high-brightness regions are merged; If the merging coefficient is less than or equal to the merging coefficient threshold, the corresponding two high-brightness regions are not merged; Repeat the above merging operation until all high-brightness regions have gone through a complete merging judgment process and there are no more region combinations that meet the merging conditions; Obtain all the merged high-brightness regions and mark them as regions to be processed; Signal generation module: Based on the regions to be processed, analyze and identify to generate analysis signals or warning signals; In some embodiments, all regions to be processed are obtained, the area value of the regions to be processed is calculated, and the area value of the regions to be processed and the total area value of the fluorescence imaging image are calculated by taking the ratio to obtain an area occupancy ratio; The area occupancy ratio is compared with the area occupancy ratio threshold. Here, the area occupancy ratio threshold is determined by those skilled in the art based on a large amount of experimental data and experience summary; If the area occupancy ratio is less than the area occupancy ratio threshold, it means that the area of the regions to be processed in the entire fluorescence imaging image accounts for a relatively small proportion, and an analysis signal is generated; If the area occupancy ratio is greater than or equal to the area occupancy ratio threshold, it means that the area of the regions to be processed in the entire fluorescence imaging image accounts for a relatively large proportion, and a warning signal is generated. Based on the warning signal, the operator adjusts the device parameters to re-obtain the fluorescence imaging image; Among them, adjusting device parameters includes but is not limited to: adjusting illumination parameters, camera parameters, and focusing parameters; The technical solution of this embodiment is as follows: Use an external endoscope device to capture a fluorescence imaging image. After preprocessing, construct a brightness histogram, set a high-brightness threshold to mark high-brightness pixel points, use them as seed points, and identify mergeable pixel points according to the pixel similarity interval to obtain a high-brightness area. Then, calculate the merge coefficient between any two high-brightness areas, compare it with the merge coefficient threshold to determine whether to merge, and finally determine the area to be processed. At the same time, the signal generation module generates an analysis signal or a warning signal according to the proportion of the area to be processed; Thus, through the system's image analysis and processing process, it is possible to accurately extract the high-brightness area from the fluorescence imaging image, reasonably merge it, determine the area to be processed, reduce the complexity caused by the excessive fragmentation of the high-brightness area to subsequent analysis, and send different signals according to the proportion of the area to be processed, providing valuable initial information for the subsequent diagnosis process, and helping the operator to adjust the device parameters in time to optimize the imaging effect. Embodiment 2

[0012] Based on the above embodiment, as Figure 1 shown, the fluorescence imaging system based on an external endoscope provided by the embodiment of the present invention specifically includes: Key area coincidence determination module: Based on the analysis signal, combined with the fluorescence map, identify whether the area to be processed is a key area; In some embodiments, based on the analysis signal, obtain the position of the area to be processed; Compare the position of the area to be processed with the fluorescence map database, and mark the diagnostic key area in the fluorescence map; Among them, the fluorescence map database is constructed based on a large amount of experimental data, clinical cases, and professional research results, covering the fluorescence characteristic information of different tissues and different disease states. For example, for the tumor detection scenario, the fluorescence map details the fluorescence intensity distribution, spectral characteristics, and fluorescence differences from the surrounding normal tissues of various tumor tissues under specific fluorescence markers; Obtain the overlapping area between the area to be processed and the diagnostic key area, calculate the ratio of the overlapping area to the area of the diagnostic key area to obtain the key area overlap ratio; Compare the key area overlap ratio with the key area overlap ratio threshold, where the key area overlap ratio threshold is determined by those skilled in the art based on a large amount of experimental data and experience summary; If the key area overlap ratio is less than the key area overlap ratio threshold, it means that the area to be processed accounts for a small area of the key area and needs further analysis, and a pre-optimization signal is generated; If the overlapping ratio of the key regions is greater than or equal to the threshold of the overlapping ratio of the key regions, it indicates that the area of the region to be processed accounts for a large proportion of the key region, which will affect the diagnostic result and generate an optimization signal; Based on the generated optimization signal, optimize the fluorescence imaging image; The ways of performing optimization processing include, but are not limited to: image enhancement optimization, noise reduction processing optimization, image restoration optimization; The technical solution of this embodiment is: based on the analysis signal generated in Embodiment 1, obtain the position of the region to be processed, compare it with the fluorescence atlas database, mark the diagnostic key region, calculate the overlapping area and overlapping ratio of the region to be processed and the diagnostic key region, compare the overlapping ratio with the threshold of the overlapping ratio of the key regions, generate a pre-optimization signal or an optimization signal, and perform corresponding processing on the fluorescence imaging image; Thus, with the help of the fluorescence atlas database, the accurate determination of whether the region to be processed is a key region is realized, and the image is optimized accordingly according to the determination result, such as enhancement, noise reduction, restoration, etc., improving the quality of the image and the accuracy of the diagnosis, avoiding the uncertainty caused by the over-brightness of the region to be processed, and further affecting the diagnostic result. Embodiment 3

[0013] Based on the above embodiments, as Figure 1 shown, the fluorescence imaging system based on an external endoscope provided by the embodiment of the present invention specifically includes: Change analysis module: Based on the pre-optimization signal, obtain the key non-overlapping region, perform multiple imaging, obtain a group of fluorescence imaging images, and perform change analysis on the pixel values of the non-overlapping region of the key region to identify whether it will affect the diagnostic result; In some embodiments, based on the pre-optimization signal, obtain the non-overlapping region of the key region and the region to be processed, and mark it as the key non-overlapping region; Obtain the fluorescence imaging maps of multiple imaging, based on any one fluorescence imaging map, obtain the pixel values of the non-overlapping region of the key region, and arrange them in the order of imaging time to obtain a pixel value sequence; Based on any group of pixel value sequences, calculate the difference between adjacent pixel values to obtain a pixel deviation value; It should be noted that when calculating the pixel deviation value, the latter pixel value is subtracted from the former pixel value; Count the number of pixel deviation values greater than zero, mark it as the number of increasing pixel values, calculate the ratio of the number of increasing pixel values to the total number of pixel deviation values to obtain the ratio of the number of increasing pixel values; Extract the pixel deviation values greater than zero, sum them up and take the average to obtain an increasing deviation average value, calculate the ratio of the increasing deviation average value to the high brightness threshold to obtain an increasing deviation average ratio; Calculate the ratio of each pixel value in the pixel value sequence to the high brightness threshold to obtain a pixel ratio sequence, calculate the standard deviation of the data in the pixel ratio sequence, and mark it as a discrete value; Perform a weighted sum calculation on the ratio of the number of growing pixel values, the mean ratio of growth deviation, and the discrete value to obtain a judgment value; The function of calculating the judgment value is as follows: First, it determines the basis for the pixels affecting the key area non-overlapping area, and screens out the potentially interfering pixels in the key area non-overlapping area. Second, it quantifies the degree of change in the pixel values in the key area non-overlapping area and its possible impact on the diagnosis. Third, it provides an important reference basis for the diagnosis decision. When there are many pixel points with judgment values greater than the threshold, it indicates that the pixel changes in the key area non-overlapping area are relatively complex and may cause greater interference to the diagnosis result; Obtain the judgment values corresponding to the pixel points in all key area non-overlapping areas to obtain a judgment value data group; Set a judgment threshold, mark the pixel points corresponding to the judgment values greater than the judgment threshold as influencing pixel points, otherwise, mark them as non-influencing pixel points; Count the number of influencing pixel points and calculate the ratio with the total number of pixel points in the key non-overlapping area to obtain the ratio of influencing pixel points; Based on any influencing pixel point, calculate the number of intervening pixels between it and the nearest pixel point, mark it as the nearest interval quantity value, sum and average the nearest interval quantity values corresponding to all influencing pixel points to obtain the nearest interval quantity mean value, and perform a ratio process on the nearest interval quantity mean value and the maximum interval quantity, and mark the obtained value as the distribution characterization value; Among them, the maximum interval quantity is the number of intervening pixels between the two pixel points with the farthest distance in the key non-overlapping area; Substitute the ratio of influencing pixel points YZ and the distribution characterization value FB into the formula , and calculate the influence coefficient YX, where a and b are preset proportional coefficients, the value of a is 1.34, and the value of b is 1.66; Compare the influence coefficient with the influence coefficient threshold. If the influence coefficient is greater than the influence coefficient threshold, it means that there are many influencing pixel points and they are relatively concentrated in the key non-overlapping area, and an influence signal is generated; Based on the influence signal, optimize and adjust the parameters of the imaging device, including but not limited to: adjusting the lighting parameters, adjusting the camera parameters, optimizing the brightness and clarity of the image, and adjusting the focusing parameters; If the influence coefficient is less than or equal to the influence coefficient threshold, it means that there are few influencing pixel points and they are relatively dispersed in the key non-overlapping area, and a non-influence signal is generated. Based on the non-influence signal, the fluorescence imaging image can be used for diagnosis; The technical solution of this embodiment is as follows: Based on the pre-optimized signal in Embodiment 2, obtain the key non-overlapping region, perform multiple imaging to obtain an image group, sort and analyze the pixel values of the key non-overlapping region according to the imaging time, calculate the ratio of the number of growing pixel values, the average growth deviation ratio, and the discrete value, perform weighted summation to obtain a judgment value, determine the influencing pixel points, and then calculate the influence coefficient. According to the comparison result between the influence coefficient and the influence coefficient threshold, generate an influence signal or a non-influence signal, and make corresponding adjustments to the imaging device parameters; Through the dynamic analysis of the pixel values in the key non-overlapping region, it is possible to quantitatively judge the influence degree of these regions on the diagnostic result. According to the influence degree, timely optimize the imaging device parameters to ensure that the fluorescence imaging image meets the diagnostic requirements, further improving the reliability and accuracy of the diagnosis, and providing a more accurate diagnostic basis for doctors. Embodiment 4

[0014] Based on the above embodiments, as Figure 2 shown, the fluorescence imaging method based on an external endoscope provided by the embodiment of the present invention specifically includes the following steps: Step 1: Obtain a fluorescence imaging image, monitor the imaging image through brightness histogram analysis and combined with an image segmentation method, obtain the high-brightness region, and perform a merging operation to determine the region to be processed; Step 2: Based on the region to be processed, perform analysis to identify and generate an analysis signal or a warning signal; Step 3: Based on the analysis signal, combine the fluorescence spectrum to identify whether the region to be processed is a key region, and generate a pre-optimized signal; Step 4: Based on the pre-optimized signal, obtain the non-overlapping region of the key region, perform multiple imaging, obtain a fluorescence imaging image group, and perform a change analysis on the pixel values of the non-overlapping region of the key region to identify whether it will affect the diagnostic result. Embodiment 5

[0015] As Figure 3 shown, the embodiment of the present invention also provides a computer device 3, including: a memory 302, a processor 301, and a computer program 303 stored on the memory 302. When the computer program 303 is executed on the processor 301, it implements the fluorescence imaging method based on an external endoscope as described in any one of the above methods.

[0016] The computer device 3 may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art can understand, Figure 3The computer device 3 is merely an example and does not constitute a limitation on the computer device 3. It may include more or fewer components than those shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0017] The so-called processor 301 may be a central processing unit (CPU), and this processor 301 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0018] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as the hard disk or memory of the computer device 3. In some other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the computer device 3. Further, the memory 302 may also include both the internal storage unit and the external storage device of the computer device 3. The memory 302 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program, etc. The memory 302 may also be used to temporarily store data that has been output or will be output. Embodiment 6

[0019] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it implements the fluorescence imaging method based on an external mirror as described in any one of the above methods.

[0020] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above embodiment methods of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0021] In the above embodiments, the descriptions of the various embodiments have their own emphases. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0022] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0023] In the embodiments disclosed in the present application, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0024] Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical, or other form.

[0025] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0026] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0027] The above has described in detail an embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. A fluorescence imaging system based on an exoscopic microscope, characterized in that: Specifically include: The module for acquiring the area to be processed is used to extract the high brightness area of ​​the fluorescent imaging image by image segmentation method, and perform a merging operation to determine the area to be processed; Signal generation module: identifies and analyzes the area to be processed and generates analysis signals; Key area overlap determination module: Based on the analysis signal, it identifies whether the area to be processed is a key area and generates a pre-optimization signal; Change analysis module: Based on the pre-optimized signal, the key non-overlapping area is obtained, and the change analysis of the pixel value is performed to obtain the affected pixel points, and identify whether it will affect the diagnosis result.

2. The exoscopic fluorescence imaging system according to claim 1, characterized in that: The acquisition process of the high brightness area is as follows: Acquire a fluorescence imaging image, perform preprocessing, and obtain pixel values; Construct a brightness histogram, where the horizontal axis is the pixel value and the vertical axis is the number of pixels corresponding to the pixel value; Mark the pixels with brightness greater than the high brightness threshold as high brightness pixels; Take high-brightness pixels as seed points, take the seed points as the starting point, traverse the pixel points in the area of ​​the seed points in order, identify whether the pixel value of each pixel point in the area is within the pixel similarity interval, and mark the pixel points with pixel values ​​in the similar interval as mergeable pixels; The mergeable pixels are used as new seed points, and the process of identifying mergeable pixels is repeated until no mergeable pixels appear. All mergeable pixels are obtained, and the positions where the mergeable pixels are located are marked as high-brightness areas.

3. The exoscopic fluorescence imaging system according to claim 1, characterized in that: The process of obtaining the area to be processed is as follows: Based on any two high-brightness areas, the pixels in the high-brightness areas are analyzed, a merging coefficient is calculated, and two high-brightness areas with a value greater than a merging coefficient threshold are merged; Repeat the above merging operation until all high-brightness areas have gone through the complete merging judgment process and there is no longer any area combination that meets the merging conditions; Get all the merged high-brightness areas and mark them as areas to be processed.

4. The exoscopic fluorescence imaging system according to claim 3, characterized in that: The process of obtaining the merging coefficient is as follows: Traverse the pixel coordinates of the two high-brightness areas respectively, count the number of pixels that belong to the two high-brightness areas at the same time, and mark them as the number of overlapping pixels; Identify the number of pixels in two high-brightness areas and compare them to extract the high-brightness area with fewer pixels; The number of overlapping pixels is processed by ratio processing with the number of pixels in the high brightness area with a small number of pixels, so as to obtain the overlap ratio value; Calculate the centroid coordinates of the two high-brightness areas respectively, and calculate the distance value between the two centroid coordinates, and perform ratio processing on the distance value and the distance standard value to obtain the distance ratio; The overlap ratio is calculated by comparing it with the distance ratio to obtain the merging coefficient.

5. The exoscopic fluorescence imaging system according to claim 1, characterized in that: The process of generating the analysis signal is as follows: Obtain all the areas to be processed, calculate the area value of the areas to be processed, and calculate the ratio with the total area value of the fluorescence imaging image to obtain the area ratio value; If the area ratio value is less than the area ratio threshold, an analysis signal is generated.

6. The exoscopic fluorescence imaging system according to claim 1, characterized in that: The process of generating the pre-optimization signal is: Based on the analysis signal, the location of the area to be processed is obtained, and compared with the fluorescence spectrum database, and the key diagnostic area is marked in the fluorescence spectrum; Obtain the overlapping area between the area to be processed and the key diagnosis area, and calculate the ratio with the area of ​​the key diagnosis area to obtain the overlapping ratio of the key area; If the overlap ratio of key areas is less than the overlap ratio threshold of key areas, a pre-optimization signal is generated.

7. The exoscopic fluorescence imaging system according to claim 1, characterized in that: The acquisition process of the influencing pixel points is as follows: Based on the pre-optimization signal, a non-overlapping area in the key area and the area to be processed is obtained and marked as a key non-overlapping area; Obtaining fluorescence imaging images of multiple imagings, obtaining all pixel values ​​of non-overlapping areas of the key area, and arranging them in the order of imaging time to obtain a pixel value sequence; Based on any set of pixel value sequences, adjacent pixel values ​​are interpolated to obtain pixel deviation values; Analyze the pixel deviation value and the pixel value, and calculate the judgment value; Obtain the judgment values ​​corresponding to the pixel points in the non-overlapping areas of all key areas to obtain a judgment value data group; The pixel points corresponding to the judgment values ​​greater than the judgment threshold are marked as influential pixels.

8. The exoscopic fluorescence imaging system according to claim 7, characterized in that: The process of obtaining the judgment value is as follows: The number of pixel deviation values ​​greater than zero is counted, marked as the number of increased pixel values, and the ratio is calculated with the total number of pixel deviation values ​​to obtain the ratio of the number of increased pixel values; Extract pixel deviation values ​​greater than zero and perform average processing to obtain the growth deviation mean, and calculate the ratio with the high brightness threshold to obtain the growth deviation mean ratio; Calculate the ratio of the pixel values ​​in the pixel value sequence to the high brightness threshold respectively to obtain a pixel ratio sequence, calculate the standard deviation of the data in the pixel ratio sequence, and mark it as a discrete value; The weighted sum of the percentage of the number of increased pixel values, the average ratio of the increased deviations and the discrete value is calculated to obtain the judgment value.

9. The exoscopic fluorescence imaging system according to claim 1, characterized in that: The process of identifying whether the diagnosis result will be affected is as follows: Perform data analysis on the affected pixels and calculate the influence coefficient; If the influence coefficient is greater than the influence coefficient threshold, an influence signal is generated; If the influence coefficient is less than or equal to the influence coefficient threshold, a non-influence signal is generated.

10. The exoscopic-based fluorescence imaging system according to claim 9, characterized in that: The process of obtaining the influence coefficient is as follows: The number of affected pixels is counted, and the ratio is calculated with the total number of pixels in the key non-overlapping area to obtain the ratio of affected pixels; Based on any influencing pixel, the number of interval pixels between it and its nearest pixel is calculated and marked as the nearest interval value. The nearest interval values ​​corresponding to all influencing pixels are averaged to obtain the nearest interval mean, which is then ratioed with the maximum interval value and the obtained value is marked as the distribution representation value. The influence coefficient is obtained by performing data calculation on the influence pixel ratio value and the distribution representation value.

Images