Nail fold microcirculation imaging method and image acquisition system

Abstract

The invention provides a nail fold microcirculation imaging method and an image acquisition system, and relates to the technical field of image processing, and the system comprises the following steps: controlling a macroscopic nail fold image acquisition module to acquire a macroscopic nail fold image, and carrying out recognition processing on the macroscopic nail fold image to obtain a nail fold contour; determining a microscopic view center point of the microscopic nail fold microcirculation image acquisition module, determining a starting point of a nail fold contour, and controlling the microscopic nail fold microcirculation image acquisition module to move to move the microscopic view center point to the starting point of the nail fold contour so as to acquire a local microscopic nail fold microcirculation image; controlling a microscopic nail fold microcirculation image acquisition module to move based on the local microscopic nail fold microcirculation image to move a microscopic view center point to a target contour point of a nail fold contour so as to acquire the local microscopic nail fold microcirculation image; and the process of collecting the local microscopic nail fold microcirculation image is repeated until the local microscopic nail fold microcirculation image comprises the end point of the nail fold contour, and collection is ended, so that the collection efficiency of nail fold microcirculation imaging can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, and in particular to a kind of nail fold microcirculation imaging method and image acquisition system. BACKGROUND

[0002] Microvascular injury is one of the pathological bases of important organ injury in rheumatic diseases, and is also an important reason for severe and fatal. Nail fold microcirculation detection is a safe, non-invasive, directly observable body surface microvascular evaluation method, which has important significance in studying the mechanism of diseases such as rheumatic diseases. Through high-resolution automatic microscopic imaging technology, accurate data collection of nail fold microcirculation can not only significantly promote the in-depth study of related diseases, but also provide an important basis for early diagnosis and treatment effect evaluation of diseases.

[0003] The resolution of the image acquisition device is low, and the entire microcirculation area cannot be covered by a single frame, so multiple microscopic fields need to be shot. In the current nail fold microcirculation imaging process, the positioning of the microscopic field depends on the subjective judgment of the operator, which leads to high operation difficulty and long acquisition time. How to improve the collection efficiency of nail fold microcirculation imaging and meet the application requirements of nail fold microcirculation detection in clinical and scientific research has become an important topic to be solved in the industry. SUMMARY

[0004] In view of the problems existing in the prior art, the present application provides a nail fold microcirculation imaging method and image acquisition system.

[0005] The present application provides a nail fold microcirculation imaging method, comprising: controlling the macroscopic nail fold image acquisition module to acquire a macroscopic nail fold image, and identifying and processing the macroscopic nail fold image to obtain a nail fold contour; determining a starting point of the nail fold contour, determining a microscopic field center point of the microscopic nail fold microcirculation image acquisition module, and controlling the microscopic nail fold microcirculation image acquisition module to move the microscopic field center point to the starting point of the nail fold contour to acquire a local microscopic nail fold microcirculation image; After obtaining the local microscopic nail fold microcirculation image, acquiring semantic information of the local microscopic nail fold microcirculation image, determining a target contour point of the nail fold contour based on the semantic information and the nail fold contour, and controlling the microscopic nail fold microcirculation image acquisition module to move the microscopic field center point to the target contour point of the nail fold contour to acquire a local microscopic nail fold microcirculation image; repeating the process after obtaining the local microscopic nail fold microcirculation image until the local microscopic nail fold microcirculation image includes an end point of the nail fold contour, and ending the acquisition of the local microscopic nail fold microcirculation image to obtain a nail fold microcirculation image.

[0006] According to the nail fold microcirculation imaging method provided by the application, the local microcosmic nail fold microcirculation image is collected, and the method comprises the following steps: Based on the first amplitude, the focusing parameter of the microcosmic nail fold microcirculation image collection module is adjusted, at least two test images are collected, and the zoom collection range and the zoom step of the focusing parameter are determined based on the image definition of the test images; Based on the zoom collection range and the zoom step, the single-focus section image is collected by the microcosmic nail fold microcirculation image collection module; The at least two single-focus section images are fused to generate a multi-focus fusion image, and the multi-focus fusion image is subjected to image enhancement processing to obtain the local microcosmic nail fold microcirculation image.

[0007] According to the nail fold microcirculation imaging method provided by the application, the microcosmic nail fold microcirculation image collection module is controlled to move the microcosmic field center point to the starting point of the nail fold contour before the local microcosmic nail fold microcirculation image is collected, and the method further comprises the following steps: The microcosmic measurement size and the microcosmic pixel equivalent of the microcosmic field of the microcosmic nail fold microcirculation image collection module are determined, and the physical measurement size of the microcosmic field is determined based on the microcosmic measurement size and the microcosmic pixel equivalent; The macroscopic pixel equivalent of the macroscopic field of the macroscopic nail fold image collection module is determined, and the frame of the microcosmic field in the macroscopic field is determined according to the physical measurement size and the macroscopic pixel equivalent; wherein the frame is synchronously moved with the microcosmic field center point.

[0008] According to the nail fold microcirculation imaging method provided by the application, the multi-focus fusion image is subjected to image enhancement processing to obtain the local microcosmic nail fold microcirculation image, and the method comprises the following steps: The multi-focus fusion image is subjected to full-image grid processing to obtain at least two grid blocks; The gray level histogram of each grid block is determined, the pixels of the grid block are subjected to clipping and mapping processing based on the gray level histogram and a preset contrast threshold value, and a preliminary enhancement image is obtained; The normalized histogram of the preliminary enhancement image is determined, the preliminary enhancement image is subjected to binarization processing based on the normalized histogram to obtain an edge black region of the preliminary enhancement image; The edge black region is subjected to illumination compensation processing to obtain the local microcosmic nail fold microcirculation image.

[0009] According to the nail fold microcirculation imaging method provided by the application, the microcosmic nail fold microcirculation image collection module is controlled to move the microcosmic field center point to the target contour point after the local microcosmic nail fold microcirculation image is collected, and the method further comprises the following steps: determining a pixel value mean and a gradient field of the local microscopic nailfold microcirculation image; determining a coordinate difference value between the microscopic field center point and the target contour point, determining a fusion region and an expansion region of a target spliced microscopic nailfold microcirculation image based on the coordinate difference value and a microscopic field of the microscopic nailfold microcirculation image acquisition module; filling the expansion region according to the pixel value mean, determining a Poisson equation of the fusion region according to the gradient field, calculating a pixel value of the fusion region by solving the Poisson equation based on a pixel value of a remaining region of the target spliced microscopic nailfold microcirculation image, and filling the fusion region.

[0010] According to the method for imaging the nailfold microcirculation provided by the application, the pixels of the grid block are cropped and mapped based on the gray histogram and a preset contrast threshold, and the method comprises the following steps: determining the number of pixels of each gray level based on the gray histogram, and cropping the pixels of the grid block based on the number of pixels of each gray level and the preset contrast threshold to obtain a cropped local microscopic nailfold microcirculation image; mapping the cropped local microscopic nailfold microcirculation image to a target space for bilinear interpolation processing.

[0011] According to the method for imaging the nailfold microcirculation provided by the application, the preliminary enhanced image is binarized based on the normalized histogram to obtain an edge black region of the preliminary enhanced image, and the method comprises the following steps: determining at least one candidate threshold, determining the inter-class variance of each candidate threshold based on the normalized histogram, and selecting the candidate threshold with the maximum inter-class variance as the gray threshold; binarizing the preliminary enhanced image based on the gray threshold to obtain the edge black region of the preliminary enhanced image.

[0012] According to the method for imaging the nailfold microcirculation provided by the application, before the edge black region is subjected to illumination compensation processing, the method further comprises the following steps: determining at least two target pixels of the edge black region, obtaining a compensation distance of the target pixels from left and right boundaries, and a maximum value of distances of respective same-row elements of the target pixels from the left and right boundaries; determining a central region average gray value and an edge black region average gray value of the preliminary enhanced image, and determining the brightness of the illumination compensation based on the central region average gray value, the edge black region average gray value, the compensation distance and the maximum value.

[0013] The application further provides a nailfold microcirculation image acquisition system, which comprises: A workbench, a macro-onychium image acquisition module is fixedly installed on the workbench, and a micro-onychium microcirculation image acquisition module is movably installed on the workbench; The macro-onychium image acquisition module is used for acquiring a macro-onychium image and sending the macro-onychium image to the image processing module; The micro-onychium microcirculation image acquisition module is used for acquiring a local micro-onychium microcirculation image and sending the local micro-onychium microcirculation image to the image processing module; The image processing module is used for realizing the onychium microcirculation imaging method according to any one of the preceding items, and the image processing module is electrically connected with the macro-onychium image acquisition module, the micro-onychium microcirculation image acquisition module and the moving platform respectively According to the onychium microcirculation image acquisition system provided by the application, the workbench comprises: A support seat, a moving platform is arranged on the top of the support seat, and a lifting platform is arranged on the bottom of the support seat; The moving platform is electrically connected with the image processing module, is used for accepting a first motion instruction of the image processing module, and drives the micro-onychium microcirculation image acquisition module to move horizontally based on the first motion instruction; The lifting platform is electrically connected with the image processing module, is used for accepting a second motion instruction of the image processing module, and moves up and down based on the second instruction.

[0014] The nail fold microcirculation imaging method and the image acquisition system provided by the application can control the macroscopic nail fold image acquisition module to acquire a macroscopic nail fold image, recognize the macroscopic nail fold image to obtain a nail fold contour, determine a starting point of the nail fold contour and a microfield center point of the microcosmic nail fold microcirculation image acquisition module, control the microcosmic nail fold microcirculation image acquisition module to move the microfield center point to the starting point of the nail fold contour to acquire a local microcosmic nail fold microcirculation image, acquire semantic information of the local microcosmic nail fold microcirculation image after the local microcosmic nail fold microcirculation image is obtained, determine a target contour point of the nail fold contour based on the semantic information and the nail fold contour, control the microcosmic nail fold microcirculation image acquisition module to move the microfield center point to the target contour point to acquire a local microcosmic nail fold microcirculation image, repeat the process after the local microcosmic nail fold microcirculation image is obtained until the local microcosmic nail fold microcirculation image includes an ending point of the nail fold contour, and end the acquisition of the local microcosmic nail fold microcirculation image to obtain a nail fold microcirculation image. The macroscopic nail fold image acquisition module independent of the microcosmic nail fold microcirculation image acquisition module is used to acquire a macroscopic nail fold image, guide the movement of the microcosmic nail fold microcirculation image acquisition module and acquire a local microcosmic nail fold microcirculation image, precise microfield positioning is provided without intervention of an operator, and therefore the acquisition efficiency of the nail fold microcirculation imaging is improved, and the application requirement of nail fold microcirculation detection in clinical and scientific research is met. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative effort.

[0016] Figure 1 is one of the flowcharts of the nail fold microcirculation imaging method provided by the application.

[0017] Figure 2 is another of the flowcharts of the nail fold microcirculation imaging method provided by the application.

[0018] Figure 3 is one of the structural diagrams of the nail fold microcirculation image acquisition system provided by the application.

[0019] Figure 4 is another of the structural diagrams of the nail fold microcirculation image acquisition system provided by the application. DETAILED DESCRIPTION

[0020] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below with reference to the drawings in the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0021] The technical solutions in the present application will be clearly and completely described below with reference to the drawings in the present application. Figures 1-4 The present application provides a nail fold microcirculation imaging method and an image acquisition system.

[0022] Figure 1 Figure 1 is one of the flow diagrams of the nail fold microcirculation imaging method provided by the present application, as shown in the figure, the method comprises the following steps: Figure 1 Step 101, controlling a macro nail fold image acquisition module to acquire a macro nail fold image, and performing recognition processing on the macro nail fold image to obtain a nail fold contour.

[0023] The macro nail fold image acquisition module is a hardware component for acquiring a macro image of a nail fold region. Illustratively, the macro nail fold image acquisition module can comprise an industrial camera with a large field of view and a telecentric lens, and by means of a tilt shooting mode combined with high-resolution imaging, the macro image of the nail fold region can be acquired without distortion at different working distances and different tilt angles.

[0024] The macro nail fold image refers to the overall image of the nail fold region, including the macro features of the nail fold contour and the surrounding tissues.

[0025] The nail fold contour refers to the macro boundary of the region where the nail fold is located. Illustratively, the macro nail fold image can be input into an image segmentation network, and the macro nail fold image can be subjected to image segmentation processing to obtain a plurality of contour points. After determining the coordinate sequence of the starting point, the ending point and the remaining contour points in the plurality of contour points, the nail fold contour can be obtained.

[0026] Step 102, determining a starting point of the nail fold contour, determining a micro visual field center point of a micro nail fold microcirculation image acquisition module, and controlling the micro nail fold microcirculation image acquisition module to move the micro visual field center point to the starting point of the nail fold contour to acquire a local micro nail fold microcirculation image.

[0027] The micro nail fold microcirculation image acquisition module is a hardware component for acquiring a nail fold microcirculation image of a nail fold region. Illustratively, the micro nail fold microcirculation image acquisition module can comprise an industrial camera with high resolution and high frame rate and a high-power lens combination, and by means of a vertical shooting mode, a high-quality local micro nail fold microcirculation image can be acquired. The high-power lens combination can comprise a microscope objective, a microscope tube lens and a liquid lens, etc.

[0028] ​Exemplarily, the corresponding pixel coordinates of the micro-visual field center point in the macro-visual field can be calculated based on the accumulated displacement information of the micro-nailfold microcirculation image acquisition module, so as to determine the micro-visual field center point of the micro-nailfold microcirculation image acquisition module. The coordinate difference between the pixel coordinates of the micro-visual field center point and the pixel coordinates of the starting point can be calculated , and the coordinate difference is multiplied by the macro-pixel equivalent to obtain the displacement control of the micro-nailfold microcirculation image acquisition module based on the movement of the micro-nailfold microcirculation image acquisition module.

[0029] Step 103: After obtaining the local micro-nailfold microcirculation image, semantic information of the local micro-nailfold microcirculation image is obtained, and a target contour point of the nailfold contour is determined based on the semantic information and the nailfold contour. The micro-nailfold microcirculation image acquisition module is controlled to move the micro-visual field center point to the target contour point of the nailfold contour to collect a local micro-nailfold microcirculation image.

[0030] The target contour point refers to the contour point of the next local micro-nailfold microcirculation image to be collected. Exemplarily, a coordinate sequence of each contour point of the nailfold contour can be determined in advance, and the next contour point of the local micro-nailfold microcirculation image to be collected is determined based on the coordinate sequence to obtain the target contour point.

[0031] The working principle of moving the micro-visual field center point to the target contour point is basically the same as that of moving the micro-visual field center point to the starting point, which will not be described here.

[0032] The semantic information of the local micro-nailfold microcirculation image refers to the information obtained by analyzing the local micro-nailfold microcirculation image, which is used to control the movement of the image acquisition module in combination with the nailfold contour. Exemplarily, the semantic information can include microcirculation blood vessel structure, microcirculation blood vessel position, blood flow characteristics, and nailfold tissue characteristics.

[0033] Step 104: The process after obtaining the local micro-nailfold microcirculation image is repeated until the local micro-nailfold microcirculation image includes the end point of the nailfold contour, and the collection of the local micro-nailfold microcirculation image to obtain the nailfold microcirculation image is ended.

[0034] The nailfold refers to a small wrinkle area at the junction of the nail and the surrounding skin, which is rich in microvessels.

[0035] Microcirculation refers to the blood circulation in the microvessels in the nailfold area. The nailfold microcirculation image can be used for observation and analysis to evaluate the morphology, function and pathological characteristics of related diseases of the microvessels.

[0036] It can be understood that the local microscopic nail fold microcirculation image can be spliced and processed as soon as a new local microcosmic nail fold microcirculation image is collected, and the nail fold microcirculation image is gradually obtained, or the local microcosmic nail fold microcirculation image at each contour point can be collected, and the nail fold microcirculation image can be spliced according to the collection sequence, and the like. In this embodiment, no further limitation is made.

[0037] The nail fold microcirculation imaging method provided in the embodiment of the application comprises the following steps: a macroscopic nail fold image collection module is controlled to collect a macroscopic nail fold image, a macroscopic nail fold image recognition module is controlled to recognize the macroscopic nail fold image to obtain a nail fold contour, a starting point of the nail fold contour and a microcosmic visual field center point of a microcosmic nail fold microcirculation image collection module are determined, the microcosmic nail fold microcirculation image collection module is controlled to move the microcosmic visual field center point to the starting point of the nail fold contour to collect a local microcosmic nail fold microcirculation image, semantic information of the local microcosmic nail fold microcirculation image is obtained after the local microcosmic nail fold microcirculation image is obtained, a target contour point of the nail fold contour is determined based on the semantic information and the nail fold contour, the microcosmic nail fold microcirculation image collection module is controlled to move the microcosmic visual field center point to the target contour point to collect a local microcosmic nail fold microcirculation image, the process of obtaining the local microcosmic nail fold microcirculation image is repeated until the local microcosmic nail fold microcirculation image includes an ending point of the nail fold contour, the collection of the local microcosmic nail fold microcirculation image is ended to obtain a nail fold microcirculation image, and a macroscopic nail fold image collection module independent of the microcosmic nail fold microcirculation image collection module is used to collect a macroscopic nail fold image, the movement of the microcosmic nail fold microcirculation image collection module and the collection of the local microcosmic nail fold microcirculation image are guided, accurate microcosmic visual field positioning is provided without the intervention of an operator, and therefore the collection efficiency of nail fold microcirculation imaging is improved, and the application requirements of nail fold microcirculation detection in clinical and scientific research are met.

[0038] It can be understood that the target contour point herein refers to a contour point of which a local microcosmic nail fold microcirculation image is to be collected next, and the process of obtaining the local microcosmic nail fold microcirculation image is repeated based on the semantic information of the local microcosmic nail fold microcirculation image collected based on a current contour point, the target contour point of the nail fold contour is determined based on the semantic information and the nail fold contour, and the microcosmic nail fold microcirculation image collection module is controlled to move the microcosmic visual field center point to the target contour point to collect a local microcosmic nail fold microcirculation image.

[0039] The ending point of the nail fold contour and the coordinates thereof can be recognized and extracted from the macroscopic nail fold image. For example, the boundary coordinates of the local microcosmic nail fold microcirculation image currently collected can be determined based on the microcosmic visual field center point coordinates, the microcosmic measurement size of the microcosmic visual field, the microcosmic pixel equivalent and the macroscopic pixel equivalent, and the ending point coordinates and the boundary coordinates of the local microcosmic nail fold microcirculation image currently collected are compared to determine whether the local microcosmic nail fold microcirculation image currently collected includes the ending point of the nail fold contour.

[0040] Based on the above embodiment, the micro-nailfold microcirculation image acquisition module can further include a cross-silk light source coaxial with the industrial camera and the high-magnification lens. When determining the micro-nailfold microcirculation image acquisition module micro-view field center point, the cross-silk light source can be turned on to obtain a cross-silk light center point. The cross-silk light center point in the macro-view field second corresponding pixel coordinate is determined. The second corresponding pixel coordinate is used to calibrate the cumulative displacement information. The corresponding pixel coordinate of the micro-nailfold microcirculation image acquisition module micro-view field center point in the macro-view field is calculated. Finally, the micro-nailfold microcirculation image acquisition module micro-view field center point is determined.

[0041] Based on any of the above embodiments, the local micro-nailfold microcirculation image is collected, including: Based on the first amplitude adjustment, the focusing parameter of the micro-nailfold microcirculation image acquisition module is adjusted. At least two test images are collected. The zoom acquisition range and the zoom step of the focusing parameter are determined based on the image clarity of the test image. Based on the zoom acquisition range and the zoom step, the micro-nailfold microcirculation image acquisition module is controlled to collect single-focus section images. At least two single-focus section images are fused to generate a multi-focus fusion image. The multi-focus fusion image is subjected to image enhancement processing to obtain the local micro-nailfold microcirculation image.

[0042] Specifically, the first amplitude refers to the zoom step of the focusing parameter of the micro-nailfold microcirculation image acquisition module for collecting test images with different image clarity. The specific value of the first amplitude can be set according to actual needs, which is not limited in the embodiment.

[0043] The focusing parameter refers to the parameter for adjusting the imaging clarity. For example, the focusing parameter can be the focusing force of the liquid lens.

[0044] The test image refers to the local micro-nailfold microcirculation image sample of the same contour point on the nailfold contour collected in the nailfold microcirculation imaging process for determining the zoom acquisition range.

[0045] The zoom acquisition range refers to the focusing parameter variation interval when quickly adjusting the focusing parameter of the micro-nailfold microcirculation image acquisition module to collect a series of single-focus section images with different clarity. For example, the multi-focus stack image fusion algorithm can be used to fuse the multiple single-focus section images obtained above to generate a multi-focus fusion image.

[0046] For example, the zoom acquisition range and the zoom step parameter can be used to control the micro-nailfold microcirculation image acquisition module to collect multiple single-focus section images. Specifically, the zoom acquisition range and the zoom step of the liquid lens can be determined according to the range of the liquid lens quick zoom 、 and the zoom step , the number of multi-focus images n in the fast zooming process is calculated, and the calculation formula is: Then, the current focusing force of the liquid lens is calculated is set to After the delay , the liquid lens is zoomed in, and the microscopic camera starts to collect images. The system gradually reduces by steps , and an image is collected after each zooming stabilization until reaches , the zooming collection process is ended.

[0047] Wherein, the specific values of each parameter are determined according to the definition method of the definition of the test image, which is not limited further in this embodiment.

[0048] Compared with the traditional preset fixed zooming range, in this embodiment, through the feedback of the image definition of multiple test images, the zooming collection range and zooming compensation of the single-focus segment image are dynamically determined, which can ensure that the single-focus segment image of each contour point of the nail fold contour is collected in the truly effective zooming collection range, reduce the risk that the image definition based on the single-focus segment image collected does not meet the demand, and improve the collection efficiency of the nail fold microcirculation imaging.

[0049] And, in this embodiment, on the basis of improving the collection efficiency of the nail fold microcirculation imaging, the single-focus segment images collected under multiple focusing parameters are fused to obtain a multi-focus fusion image, and the multi-focus fusion image is subjected to image enhancement processing, which can improve the quality of the final nail fold microcirculation image while reducing the calculation resources consumed by the image enhancement processing.

[0050] Based on any of the above embodiments, before controlling the microscopic nail fold microcirculation image collection module to move the microscopic field center point to the starting point of the nail fold contour to collect a local microscopic nail fold microcirculation image, the method further comprises: determining the microscopic dimension and the microscopic pixel equivalent of the microscopic field of the microscopic nail fold microcirculation image collection module, and determining the physical dimension of the microscopic field based on the microscopic dimension and the microscopic pixel equivalent; determining the macroscopic pixel equivalent of the macroscopic field of the macroscopic nail fold image collection module, and determining the frame of the microscopic field in the macroscopic field according to the physical dimension and the macroscopic pixel equivalent; wherein the frame moves synchronously with the microscopic field center point.

[0051] Specifically, the microscopic field of view refers to the visible area that can be collected by the microscopic nailfold microcirculation image collection module in a single collection. It can be understood that the size of the microscopic field of view is determined by the optical magnification of the microscopic nailfold microcirculation image collection module and the imaging sensor size and other parameters.

[0052] The microscopic metric size is used to describe the composition of the microscopic field of view on the imaging sensor; the microscopic pixel equivalent is used to describe the physical size corresponding to the pixels of the microscopic field of view in the actual sample, for example, the physical size corresponding to the pixels on the real nailfold tissue. Exemplarily, the product of the microscopic metric size and the microscopic pixel equivalent can be calculated to determine the physical metric size of the microscopic field of view.

[0053] The macroscopic field of view refers to the visible area that can be collected by the macroscopic nailfold image collection module in a single collection. It can be understood that the size of the macroscopic field of view is determined by the optical magnification of the macroscopic nailfold image collection module and the imaging sensor size and other parameters.

[0054] The macroscopic pixel equivalent is used to describe the physical size corresponding to the pixels of the macroscopic field of view in the actual sample. Exemplarily, the quotient of the physical metric size and the macroscopic pixel equivalent can be calculated to determine the macroscopic metric size of the microscopic field of view in the macroscopic field of view, based on which the size of the frame is determined, and the center point of the microscopic field of view is determined as the center of the frame to determine the frame of the microscopic field of view in the macroscopic field of view. The frame and the center point of the microscopic field of view are associated by an algorithm to realize synchronous movement of the two.

[0055] In another embodiment, the quotient of the physical metric size and the macroscopic pixel equivalent is calculated to determine the size of a single microscopic field of view in the macroscopic imaging coordinate system , and the product of and the macroscopic scaling coefficient is further calculated to determine the macroscopic metric size of the microscopic field of view in the macroscopic field of view, based on which the size of the frame is determined. The macroscopic scaling coefficient is the ratio of the image resolution of the macroscopic display coordinate system to the image resolution of the macroscopic imaging coordinate system .

[0056] In this embodiment, the real-time feedback of the synchronous movement of the frame and the center point of the microscopic field of view can facilitate the user to quickly and accurately locate the current collection area of the microscopic nailfold microcirculation image collection module; the size conversion of the microscopic metric size, the physical metric size and the macroscopic metric size to determine the frame of the microscopic field of view in the macroscopic field of view can improve the accuracy of the frame in the macroscopic field of view to represent the collection position of the microscopic field of view, and improve the reliability of the real-time feedback.

[0057] Based on any of the above embodiments, the multi-focus fusion image is subjected to image enhancement processing to obtain the local microscopic nailfold microcirculation image, which includes: performing full-image grid processing on the multi-focus fusion image to obtain at least two grid blocks; determining a gray level histogram of each of the grid blocks, performing clipping and mapping processing on pixels of the grid blocks based on the gray level histogram and a preset contrast threshold to obtain a preliminary enhanced image; determining a normalized histogram of the preliminary enhanced image, and performing binarization processing on the preliminary enhanced image based on the normalized histogram to obtain an edge black region of the preliminary enhanced image; performing illumination compensation processing on the edge black region to obtain the local microscopic nailfold microcirculation image.

[0058] Specifically, the grid block refers to a plurality of small rectangular image regions obtained by performing full-image grid processing on the multi-focus fusion image.

[0059] The contrast threshold is used to limit the maximum value of the number of pixels of each gray level in the gray level histogram of each grid block. The specific value of the contrast threshold can be set according to actual needs, and the present embodiment does not make further limitations thereon.

[0060] For example, the part of the number of pixels of each gray level in the gray level histogram of each grid block that exceeds the contrast threshold can be clipped, and the clipped pixels can be distributed to other gray levels of the gray level histogram for mapping processing, so as to enhance the contrast of the multi-focus fusion image and obtain the preliminary enhanced image.

[0061] The normalized histogram is used to describe the gray level characteristics of the preliminary enhanced image after gray level transformation. For example, the normalized histogram can be obtained by performing normalization processing on the gray level histogram. The edge black region refers to a region with low brightness determined based on the illumination distribution boundary line segmented by performing binarization processing on the preliminary enhanced image.

[0062] On the basis of the details of the nailfold microcirculation image, in the present embodiment, the local contrast of the multi-focus fusion image can be enhanced by grid division and contrast threshold processing of the multi-focus fusion image, the definition of the structure such as blood vessels in the multi-focus fusion image is preliminarily increased, on this basis, the positioning accuracy of the edge black region is further increased by normalization histogram and binarization processing, the illumination compensation of the preliminary enhanced image is targeted, and the uniformity of the obtained local microscopic nailfold microcirculation image is improved, so as to improve the image quality of the local microscopic nailfold microcirculation image as a whole.

[0063] Based on any of the above embodiments, the clipping and mapping processing on the pixels of the grid blocks based on the gray level histogram and the preset contrast threshold comprises: determine the number of pixels of each gray level based on the gray histogram, and perform cropping on the pixels of the grid block based on the number of pixels of each gray level and a preset contrast threshold to obtain a cropped local microscopic nail fold microcirculation image; perform bilinear interpolation processing on the cropped local microscopic nail fold microcirculation image in a target space.

[0064] Specifically, the cropped local microscopic nail fold microcirculation image refers to an image obtained by cropping pixels of a target field local microscopic nail fold microcirculation image based on a contrast threshold.

[0065] For example, the cropped local microscopic nail fold microcirculation image can be subjected to equalization processing, the gray value distribution is mapped to a new space, and bilinear interpolation is performed on each grid block in combination with the mapping results of adjacent blocks to obtain a preliminary enhanced image. The mapping of the gray value distribution to the new space can refer to the value range of the new pixel gray value. The bilinear interpolation can be performed in combination with the mapping results of the adjacent four blocks.

[0066] In an embodiment, after the bilinear interpolation, Gaussian blur processing is further performed to obtain the preliminary enhanced image.

[0067] Based on any of the above embodiments, the binarization processing of the preliminary enhanced image based on the normalized histogram to obtain the edge black region of the preliminary enhanced image comprises: determining at least one candidate threshold, determining the inter-class variance of each candidate threshold based on the normalized histogram, and selecting the candidate threshold with the maximum inter-class variance as the gray threshold; performing binarization processing on the preliminary enhanced image based on the gray threshold to obtain the edge black region of the preliminary enhanced image.

[0068] Specifically, the candidate threshold refers to a series of possible gray values selected in the process of binarization processing of the preliminary enhanced image in order to determine the best image segmentation threshold.

[0069] The gray threshold is a gray value corresponding to the best segmentation effect in the segmentation effect obtained by binarization processing from a series of possible gray values.

[0070] For example, the cumulative probability and the mean value can be calculated based on the normalized histogram, and the global mean value of the preliminary enhanced image is calculated at the same time. The inter-class variance of each candidate threshold is determined based on the global mean value and the normalized histogram.

[0071] Based on any of the above embodiments, before the illumination compensation processing is performed on the edge black region, the method further comprises: determining at least two target pixels of the edge black region, obtaining a compensation distance of the target pixels to the left and right boundaries, and a maximum value of distances of respective same-row elements of the target pixels to the left and right boundaries; determining a central region average gray value and an edge black region average gray value of the preliminary enhanced image, and determining a light compensation brightness based on the central region average gray value, the edge black region average gray value, the compensation distance and the maximum value.

[0072] Specifically, the compensation distance refers to a distance of the target pixels to the left and right boundaries, which is used to calculate the light compensation brightness.

[0073] The central region can refer to a part of the image except the edge black region, or a region of a set size centered on a center of the preliminary enhanced image, etc., which can be set according to actual needs, and the embodiment is not limited further.

[0074] In an embodiment, the light compensation brightness can be determined by the following formula : wherein, the compensation distance of the target pixels to the left and right boundaries, the maximum value of distances of the same-row elements of the target pixels to the left and right boundaries, the central region average gray value, the edge black region average gray value.

[0075] Compared with fixed brightness compensation, in the embodiment, a difference between the central region average gray value and the edge region average gray value is calculated to determine a degree of light unevenness in the preliminary enhanced image, so as to adaptively determine the light compensation brightness; and the compensation distance and the maximum value are used to realize that the compensation brightness gradually changes with the pixel position, so as to avoid a risk of brightness mutation of the edge black region, and increase a natural degree and a smooth degree of the brightness compensation effect.

[0076] Based on any of the above embodiments, after the microscopic nailfold microcirculation image acquisition module is controlled to move the microscopic visual field center point to the target contour point to acquire the local microscopic nailfold microcirculation image, the method further comprises: determining a pixel value mean and a gradient field of the local microscopic nailfold microcirculation image; determining a coordinate difference value of the microscopic visual field center point and the target contour point, and determining a fusion region and an expansion region of a target spliced microscopic nailfold microcirculation image based on the coordinate difference value and a microscopic visual field of the microscopic nailfold microcirculation image acquisition module; Filling the expansion region according to the mean value of the pixel values; determining a Poisson equation of the fusion region according to the gradient field, calculating the pixel values of the fusion region by solving the Poisson equation based on the pixel values of the remaining region of the target spliced micro-onychium microcirculation image, and filling the fusion region.

[0077] Specifically, the target spliced micro-onychium microcirculation image refers to an image obtained by expanding the size of a current spliced micro-onychium microcirculation image. The current spliced micro-onychium microcirculation image can be a micro-onychium microcirculation image collected at a starting point, or a micro-onychium microcirculation image spliced by a plurality of local micro-onychium microcirculation images collected before the target contour point.

[0078] The fusion region refers to an overlapping part of the target spliced micro-onychium microcirculation image and the current spliced micro-onychium microcirculation image collected by the target contour point. The expansion region refers to a newly added non-overlapping part of the target spliced micro-onychium microcirculation image and the current spliced micro-onychium microcirculation image collected by the target contour point. The remaining region refers to an original non-overlapping part of the target spliced micro-onychium microcirculation image and the current spliced micro-onychium microcirculation image collected by the target contour point.

[0079] For example, the size of the current spliced micro-onychium microcirculation image is (100, 150), the coordinate difference of the center point of the micro-view field is (0, 50), the size of the target spliced micro-onychium microcirculation image obtained is (100, 200), and the size of the local micro-onychium microcirculation image is (100, 100). The 100-150 region of the y-axis is the fusion region, and the 150-200 region is the expansion region.

[0080] In an embodiment, the pixel values of the remaining region of the target spliced micro-onychium microcirculation image can be used as a boundary condition to solve the Poisson equation to obtain the pixel values of the fusion region.

[0081] In this embodiment, the fusion region and the expansion region of the target spliced micro-onychium microcirculation image are accurately calculated according to the movement of the micro-view field, which reduces the risk of errors such as misplacement and ghosting in splicing. Different filling methods are used for the expansion region and the fusion region. The expansion region is preliminarily processed by mean value filling, and the fusion region is processed by Poisson fusion, which can achieve natural splicing while balancing the calculation complexity.

[0082] As shown in FIG. 1, Figure 2 To specifically illustrate the function of the onychium microcirculation imaging method provided in the embodiment, a specific example is provided as follows.

[0083] After the start process of the nail fold microcirculation imaging collection, a macroscopic nail fold image is collected by controlling a macroscopic nail fold image collection module, a starting point of a nail fold contour and a microscopic field center point of a microscopic nail fold microcirculation image collection module are determined, the microscopic field center point is moved to the starting point of the nail fold contour to realize field initialization; At least two test images are collected based on the first amplitude adjustment of the focusing parameter of the microscopic nail fold microcirculation image collection module, a zoom collection range and a zoom step of the focusing parameter are determined based on the image definition discrimination of the test images, a plurality of single-focus section images are obtained by rapid multi-focusing collection, and a multi-focus fusion image is generated by fusion processing; the multi-focus fusion image is enhanced to obtain a local microscopic nail fold microcirculation image; After obtaining the local microscopic nail fold microcirculation image of the starting point, a target contour point of the nail fold contour is determined, and the microscopic nail fold microcirculation image collection module is controlled to move the microscopic field center point to the target contour point; At least two test images are collected based on the first amplitude adjustment of the focusing parameter of the microscopic nail fold microcirculation image collection module, a zoom collection range and a zoom step of the focusing parameter are determined based on the image definition discrimination of the test images, a plurality of single-focus section images are obtained by rapid multi-focusing collection, and a multi-focus fusion image is generated by fusion processing; The multi-focus fusion image is enhanced to obtain a local microscopic nail fold microcirculation image, and Poisson fusion processing is performed on adjacent local microscopic nail fold microcirculation images to obtain a current spliced microscopic nail fold microcirculation image. In the case that the local microscopic nail fold microcirculation image includes the termination point of the nail fold contour, the collection of the local microscopic nail fold microcirculation image is ended to obtain a nail fold microcirculation image.

[0084] The nail fold microcirculation image collection system provided by the application is described below, and the nail fold microcirculation image collection system described below can be correspondingly referred to the nail fold microcirculation imaging method described above.

[0085] Figure 3 The nail fold microcirculation image collection system provided by the application is described below, and the nail fold microcirculation image collection system described below can be correspondingly referred to the nail fold microcirculation imaging method described above. Figure 3 As shown in the structure diagram, the system comprises: A workbench, wherein a macroscopic nail fold image collection module is fixedly installed on the workbench, and a microscopic nail fold microcirculation image collection module is movably installed on the workbench; The macroscopic nail fold image collection module is used for collecting a macroscopic nail fold image and sending the macroscopic nail fold image to an image processing module; The microscopic nail fold microcirculation image collection module is used for collecting a local microscopic nail fold microcirculation image and sending the local microscopic nail fold microcirculation image to an image processing module; An image processing module is configured to implement the nail fold microcirculation imaging method according to any one of the preceding aspects, and is electrically connected to the macroscopic nail fold image acquisition module, the microscopic nail fold microcirculation image acquisition module and the moving platform, respectively.

[0086] For example, the macroscopic nail fold image acquisition module can include a macroscopic camera 1 and a telecentric lens 2, and the microscopic nail fold microcirculation image acquisition module can include a microscopic camera 3 and a microscope lens combination 4.

[0087] As shown in Figure 4 According to any one of the preceding aspects, the workbench includes: A support base, the top of which is provided with the moving platform 5, and the bottom of which is provided with the lifting platform 6; The moving platform 5 is fixedly installed with the microscopic nail fold microcirculation image acquisition module, and is electrically connected to the image processing module, configured to receive a first motion instruction of the image processing module, and move the microscopic nail fold microcirculation image acquisition module horizontally based on the first motion instruction. The lifting platform 6 is provided with an image acquisition area, and is electrically connected to the image processing module, configured to receive a second motion instruction of the image processing module, and move up and down based on the second instruction.

[0088] The system embodiments described above are only illustrative, wherein the units illustrated as separate components can or can not be physically separated, and the components illustrated as units can or can not be physical units, i.e., can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0089] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software and necessary universal hardware platforms, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.

[0090] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit the same; and although the present application has been described in detail with reference to the foregoing embodiments, it should be appreciated by those skilled in the art that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features thereof can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A nailfold microcirculation imaging method, characterized in that: include: controlling the macro nail fold image acquisition module to acquire a macro nail fold image, and performing recognition processing on the macro nail fold image to obtain a nail fold contour; Determining the starting point of the nail fold outline, determining the center point of the microscopic field of view of the microscopic nail fold microcirculation image acquisition module, and controlling the movement of the microscopic field of view to move the center point to the starting point of the nail fold outline to acquire a local microscopic nail fold microcirculation image; After obtaining the local microscopic nailfold microcirculation image, semantic information of the local microscopic nailfold microcirculation image is acquired, a target contour point of the nailfold contour is determined based on the semantic information and the nailfold contour, and the microscopic nailfold microcirculation image acquisition module is controlled to move the center point of the microscopic field of view to the target contour point of the nailfold contour to acquire the local microscopic nailfold microcirculation image; Repeat the process of obtaining the local microscopic nail fold microcirculation image until the local microscopic nail fold microcirculation image includes the end point of the nail fold contour, and end the acquisition of the local microscopic nail fold microcirculation image to obtain the nail fold microcirculation image.

2. The nailfold microcirculation imaging method according to claim 1, characterized in that: Acquire local microscopic nailfold microcirculation images, including: Adjusting the focus parameter of the microscopic nailfold microcirculation image acquisition module based on the first amplitude, acquiring at least two test images, and determining the zoom acquisition range and zoom step of the focus parameter based on the image clarity of the test images; Controlling the microscopic nailfold microcirculation image acquisition module to acquire a single focal segment image based on the zoom acquisition range and the zoom step size; At least two of the single-focus images are fused to generate a multi-focus fusion image, and the multi-focus fusion image is enhanced to obtain the local microscopic nailfold microcirculation image.

3. The nailfold microcirculation imaging method according to claim 1, characterized in that: Before controlling the microscopic nail fold microcirculation image acquisition module to move the center point of the microscopic field of view to the starting point of the nail fold outline to acquire a local microscopic nail fold microcirculation image, the method further includes: Determining a microscopic metric size and a microscopic pixel equivalent of a microscopic field of view of a microscopic nailfold microcirculation image acquisition module, and determining a physical metric size of the microscopic field of view based on the microscopic metric size and the microscopic pixel equivalent; Determine the macro pixel equivalent of the macro field of view of the macro nail fold image acquisition module, and determine the border of the micro field of view in the macro field of view according to the physical measurement size and the macro pixel equivalent; wherein the border moves synchronously with the center point of the micro field of view.

4. The nailfold microcirculation imaging method according to claim 2, characterized in that: The performing image enhancement processing on the multi-focus fusion image to obtain the local microscopic nailfold microcirculation image includes: Performing full-image gridding processing on the multi-focus fusion image to obtain at least two grid blocks; Determining a grayscale histogram of each grid block, and performing cropping and mapping processing on pixels of the grid block based on the grayscale histogram and a preset contrast threshold to obtain a preliminary enhanced image; Determining a normalized histogram of the preliminary enhanced image, and performing binarization processing on the preliminary enhanced image based on the normalized histogram to obtain a black edge area of ​​the preliminary enhanced image; Light compensation processing is performed on the edge black area to obtain the local microscopic nail fold microcirculation image.

5. The nailfold microcirculation imaging method according to claim 1, characterized in that: After controlling the microscopic nailfold microcirculation image acquisition module to move the microscopic field center point to the target contour point to acquire the local microscopic nailfold microcirculation image, the method further includes: determining a pixel value mean and a gradient field of the local microscopic nailfold microcirculation image; Determining a coordinate difference between the center point of the microscopic field of view and the target contour point, and determining a fusion area and an expansion area of ​​the target stitched microscopic nailfold microcirculation image based on the coordinate difference and the microscopic field of view of the microscopic nailfold microcirculation image acquisition module; The expanded area is filled according to the mean value of the pixel value; the Poisson equation of the fusion area is determined according to the gradient field, the pixel value of the fusion area is obtained by calculating the Poisson equation based on the pixel value of the remaining area of ​​the target spliced ​​microscopic nailfold microcirculation image, and the fusion area is filled.

6. The nailfold microcirculation imaging method according to claim 4, characterized in that: The clipping and mapping processing of the pixels of the grid block based on the grayscale histogram and a preset contrast threshold comprises: Determining the number of pixels at each gray level based on the gray level histogram, and cropping the pixels of the grid block based on the number of pixels at each gray level and a preset contrast threshold to obtain a cropped local microscopic nail fold microcirculation image; The cropped local microscopic nailfold microcirculation image is mapped to the target space and bilinear interpolation is performed.

7. The nailfold microcirculation imaging method according to claim 4, characterized in that: The binarization processing of the preliminary enhanced image based on the normalized histogram to obtain the edge black area of ​​the preliminary enhanced image includes: Determine at least one candidate threshold, determine the inter-class variance of each candidate threshold based on the normalized histogram, and select the candidate threshold with the largest inter-class variance as the grayscale threshold; The preliminary enhanced image is binarized based on the grayscale threshold to obtain an edge black area of ​​the preliminary enhanced image.

8. The nailfold microcirculation imaging method according to claim 4, characterized in that: Before performing illumination compensation processing on the edge black area, the method further includes: Determine at least two target pixels in the edge black area, and obtain the maximum value of the compensation distances between the target pixels and the left and right boundaries, and the distances between each in-line element of the target pixel and the left and right boundaries; Determine the average grayscale value of the central area and the average grayscale value of the edge black area of ​​the preliminary enhanced image, and determine the brightness of the illumination compensation based on the average grayscale value of the central area, the average grayscale value of the edge black area, the compensation distance and the maximum value.

9. A nail fold microcirculation image acquisition system, characterized in that: include: A workbench, on which a macroscopic nailfold image acquisition module is fixedly installed and a microscopic nailfold microcirculation image acquisition module is movably installed; A macroscopic nail fold image acquisition module is used to acquire a macroscopic nail fold image and send the macroscopic nail fold image to an image processing module; A microscopic nail fold microcirculation image acquisition module is used to acquire a local microscopic nail fold microcirculation image and send the local microscopic nail fold microcirculation image to the image processing module; An image processing module is used to implement the nail fold microcirculation imaging method described in any one of claims 1 to 8, and the image processing module is electrically connected to the macro nail fold image acquisition module, the micro nail fold microcirculation image acquisition module and the mobile platform respectively.

10. The nailfold microcirculation image acquisition system according to claim 9, characterized in that: The workbench comprises: A support base, wherein a motion platform is provided on the top of the support base and a lifting platform is provided on the bottom; a motion platform, on which the microscopic nailfold microcirculation image acquisition module is fixedly mounted, the motion platform being electrically connected to the image processing module and configured to receive a first motion instruction from the image processing module and drive the microscopic nailfold microcirculation image acquisition module to move horizontally based on the first motion instruction; A lifting platform is provided with an image acquisition area, and the lifting platform is electrically connected to the image processing module, and is used to receive a second motion instruction from the image processing module and move up and down based on the second motion instruction.

Images