A method and system for rapid identification and imaging of oral vascular abnormality areas

Abstract

The present invention relates to the field of image processing, and provides a method and system for rapid identification and imaging of abnormal areas of oral blood vessels, wherein an imaging scan is performed on the oral area of ​​a patient to obtain an initial image, the initial image is subjected to foreground extraction and division to obtain multiple foreground target areas, and an edge co-solution value is calculated according to the pixel distribution of the initial image, and the initial image is subjected to pixel adjustment by the edge co-solution value to obtain an output image. The method can effectively identify and highlight the pixel information of abnormal areas in oral blood vessels, and by foreground extraction and analyzing the edge information of sub-areas, the initial image is subjected to pixel adjustment in a local range, which can effectively enhance the details and pixel contrast of the abnormal area, and enhance the high recognition of vascular tissue while retaining the real information of the image, and at the same time, the pixel processing method of each area can accelerate the process of identification and imaging, and improve the accuracy of image processing.

Description

Technical Field

[0001] The invention relates to the field of image processing, and in particular to a method for rapid identification and imaging of oral vascular abnormality areas. Background Art

[0002] Traditional oral medical imaging technology has disadvantages such as time-consuming process and limited accuracy. With the development of ultrasonic imaging and computer vision, the accuracy and efficiency of imaging detection have been improved, but there are still some limitations, such as high cost and slow processing speed.

[0003] Invention patent CN117058309B discloses an image generation method based on oral imaging, which specifically includes generating a corresponding oral image by comparing oral CT image data covering soft tissue with a second oral model scanned by laser three-dimensional scanning, thereby avoiding the existing collection and analysis of pathological soft tissues such as muscles and / or tumors only through optical images, which leads to the need for image stitching in the case of multiple optical image data, and thus easily leads to image distortion.

[0004] To address this problem, a method based on the first edge smoothness and the second edge smoothness is used to correct the feature data in the image, and the final oral three-dimensional image model is obtained by marking and eliminating multiple difference structure areas. However, in practical applications, edge blurring and excessive smoothing often cause the loss of key pathological information, especially the boundaries of pathological tissues such as oral soft tissue or tumors are usually not clear. Over-reliance on edge smoothness will cause these subtle features to be blurred too much, resulting in the loss of feature pixels, thus affecting the quality of the final generated image.

[0005] In summary, when using Doppler color ultrasound imaging or optical coherence tomography to detect and diagnose oral vascular abnormalities (such as hemangiomas or vascular malformations), the vascular structure is difficult to distinguish from the surrounding tissue due to the similar contrast of the soft tissue in the oral cavity, resulting in insufficient recognition accuracy of tiny vascular abnormalities during the imaging process, affecting the imaging quality and making it difficult to meet the high-precision diagnostic needs for rapid formation and evaluation of clinical plans. Therefore, a high-visualization imaging method using image enhancement is the key to identifying oral vascular abnormality areas and improving its recognition efficiency and accuracy. Summary of the invention

[0006] The purpose of the present invention is to provide a method for rapid identification and imaging of abnormal oral vascular areas to solve one or more technical problems existing in the prior art and at least provide a beneficial option or create conditions.

[0007] The present invention provides a method and system for rapid identification and imaging of abnormal areas of oral blood vessels, wherein an imaging scan is performed on the oral area of ​​a patient to obtain an initial image, the initial image is subjected to foreground extraction and division to obtain multiple foreground target areas, and an edge co-solution value is calculated according to the pixel distribution of the initial image, and the initial image is subjected to pixel adjustment by the edge co-solution value to obtain an output image. The method can effectively identify and highlight the pixel information of abnormal areas in oral blood vessels, and by foreground extraction and analyzing the edge information of sub-areas, the initial image is subjected to pixel adjustment in a local range, which can effectively enhance the details and pixel contrast of the abnormal area, and enhance the high recognition of vascular tissue while retaining the real information of the image. At the same time, the pixel processing method of each area can accelerate the process of identification and imaging, and improve the accuracy of image processing.

[0008] In order to achieve the above object, according to one aspect of the present invention, a method for rapid identification and imaging of oral vascular abnormality areas is provided, the method comprising the following steps:

[0009] Perform an imaging scan of the patient's oral region to obtain an initial image;

[0010] Extract and divide the foreground of the initial image to obtain multiple foreground target areas;

[0011] According to the pixel distribution of the initial image, the edge co-solution value is calculated;

[0012] The initial image is pixel-adjusted using the edge co-solution value to obtain the output image.

[0013] Furthermore, the method of imaging and scanning the oral area of ​​the patient to obtain the initial image is specifically: capturing and imaging the area inside the patient's oral cavity through an electronic fluorescence endoscope, or imaging and scanning the oral area of ​​the patient through an oral scanner to obtain a color initial image.

[0014] Furthermore, the method of performing foreground extraction and division on the initial image to obtain multiple foreground target areas is as follows: performing foreground extraction (or background separation) on the initial image through an edge detection algorithm or an image segmentation algorithm to obtain the foreground part of the initial image, recording the foreground part as a large area, and dividing the large area into M sub-areas (by dividing the sub-areas, block processing of the abnormal area of ​​the oral cavity is achieved to improve the processing speed and the quality and effect of the image generated after processing), and using these M areas as M foreground target areas (the foreground target areas are closed areas).

[0015] Preferably, the value of M is set to an integer in the interval [5,30].

[0016] Optionally, the edge detection algorithm is a Sobel edge detection algorithm, and the image segmentation algorithm is a region growing algorithm.

[0017] Optionally, foreground extraction is performed on the initial image, and the foreground extraction method is GrabCut algorithm.

[0018] Furthermore, the edge co-solution value is calculated based on the pixel distribution of the initial image, wherein the method for obtaining the pixel distribution of the initial image is specifically: fgd(j) represents the j-th foreground target area among M foreground target areas, all boundary pixels of fgd(j) are screened out in the initial image, and the sum of the pixel values ​​of all boundary pixels of fgd(j) is recorded as Mf(j), then the M foreground target areas fgd(1), fgd(2),…, fgd(M) correspond to M values ​​Mf(1), Mf(2),…, Mf(M).

[0019] Furthermore, according to the pixel distribution of the initial image, the method for calculating the edge common solution value is specifically: calculating the variance of the M values ​​Mf(1), Mf(2), ..., Mf(M), and taking the variance as the edge common solution value.

[0020] Since complex images usually contain multiple types of edge features (such as edges of different directions and intensities), using the global variance of the pixel values ​​of all boundary pixels cannot effectively capture these details, because the variance only provides a global value and cannot characterize the diverse edge morphology and structure. In this way, fine edge features will be smoothed, resulting in local information loss and poor edge detection effect. Therefore, a method for calculating edge consensus value based on edge information quantification is provided:

[0021] Preferably, according to the pixel distribution of the initial image, the method for calculating the edge co-solution value may also be:

[0022] Create a blank array Mf[], add M values ​​Mf(1), Mf(2), …, Mf(M) to the array Mf[] in sequence, then the j-th value in the array Mf[] is represented as Mf(j);

[0023] Subtract the minimum value in array Mf[] from the M values ​​in array Mf[] to obtain M first values, negate the M first values, and exponentially perform the exponential operation on the M first values ​​after negation with the natural constant e to obtain M second values, multiply the M second values ​​with the M values ​​in array Mf[] in sequence to obtain M third values, divide the maximum value in array Mf[] by the M third values ​​in sequence to obtain M fourth values, add up the M fourth values, and record the value obtained after addition as the marginal common solution value Ecv.

[0024] The beneficial effect of this step is: in the medical image analysis technology of oral imaging, the edge information of the image is crucial to identifying and distinguishing vascular tissue. However, due to interference factors such as equipment hardware limitations and lighting conditions, the initial image is prone to the problem that the edge information is not prominent enough relative to other pixel information in the image. Therefore, the method of this step compares the sum of the boundary pixels of each foreground target area with its minimum value and normalizes it with its maximum value to quantify the edge information of each foreground target area, thereby providing a unified benchmark calculation for the subsequent pixel adjustment of the initial image.

[0025] Furthermore, all boundary pixels of fgd(j) are screened out in the initial image, wherein all boundary pixels refer to all pixels constituting the boundary of fgd(j) (or all pixels located in the outermost layer of fgd(j)).

[0026] Further, the method of adjusting pixels of the initial image by edge co-solution values ​​to obtain an output image is specifically as follows: sharpening all pixels in the initial image by an unsharp masking method, saving the sharpened initial image as an output image, and outputting the output image to a display;

[0027] In the unsharp masking method, the specific value of the parameter sharpening amount (Amount) is set to the edge common solution value.

[0028] The unsharp masking algorithm in the sharpening processing technology requires setting three parameters: the total amount of sharpening (Amount), radius (Radius), and threshold (Threshold). Among them, the change of the total amount of sharpening has a higher sensitivity to the sharpening effect than the other two parameters, radius and threshold.

[0029] In the Unsharp Masking algorithm, the image is sharpened by enhancing the high-frequency components (edges) of the image. The usual practice is to first smooth the image (for example, by Gaussian blur), then subtract the blurred image from the original image to obtain the so-called "edge image" or "difference image", and then combine it with the original image to enhance the edge details of the image. The intensity of sharpening is controlled by the parameter Amount (total amount of sharpening), which determines the degree of edge enhancement. Using the edge co-solution value as the adaptive parameter of Amount in Unsharp Masking will bring the following defects:

[0030] Since image noise contains high-frequency components, when calculating the edge co-solution value based on global variance or edge information quantization, the co-solution value in the noise area is often larger, thereby triggering a stronger sharpening effect. In some smooth transition areas (such as gradient areas) or areas with smaller details, the edge co-solution value is not only high at the actual image edge, but may also produce high values ​​in noise points or areas with random high-frequency components. Using the edge co-solution value as a parameter for the sharpening amount will introduce over-sharpening in these noise areas, causing the noise to be amplified and the image quality to deteriorate.

[0031] Therefore, a method for output image optimization based on post-processing pixel compensation is proposed:

[0032] Preferably, the method of adjusting the pixels of the initial image by edge co-solution values ​​to obtain the output image may also be:

[0033] S1, set variable k = 1, the value range of variable k is the same as the value range of j, and go to S2;

[0034] S2, let fgd(k) contain N(k) pixels, N(k) is a variable, each pixel corresponds to a pixel value, and the pixel values ​​of these N(k) pixels are adjusted in turn, and then go to S3;

[0035] S3, if the value of variable k is less than M, then increase the value of k by 1 (increment k to enter the next foreground target area), and go to S2; if the value of variable k is greater than or equal to M (when k=M, it means that the pixels in the M foreground target areas have been adjusted and the traversal is completed), then go to S4;

[0036] S4, saving the initial image after pixel adjustment as an output image, and outputting the output image to a display.

[0037] The beneficial effect of this step is: in the process of identifying and imaging the abnormal area of ​​oral blood vessels, the image quality can affect the specific diagnosis plan. Due to the limitations of imaging technology and its resolution, various image noises often appear in the acquisition process of oral imaging, resulting in slight structural changes and loss of details. At the same time, due to the dynamic range limitations of medical imaging equipment, image information will be distorted in areas that are too dark or too bright, which needs to be compensated through post-processing. The method of this step processes each pixel in each foreground target area separately, optimizes it separately according to the pixel information of the area where each pixel is located, dynamically adjusts the pixel value intensity with the pixel value of each pixel and its eight neighborhoods, and uses the pixel correlation between neighboring pixels to retain and enhance the key information of the image (abnormal area), greatly improving the contrast and details of the local area, highlighting the slight changes in vascular tissue in the oral area, and improving the quality and authenticity of imaging.

[0038] Furthermore, the method of sequentially adjusting the pixel values ​​of the N(k) pixels is specifically as follows:

[0039] S21, p(k,i) represents the i-th pixel among the N(k) pixels, initialize a variable r, the value range of r is the same as the value range of i, set the initial value of r to r=1 (use r as the sequence number traversal variable to traverse and adjust N(k) pixels), and go to S22;

[0040] S22, record the average value of all pixels in the eight neighborhoods of p(k,r) as En(r), if the value of En(r) is less than Ecv, go to S23; if the value of En(r) is greater than or equal to Ecv, go to S24;

[0041] S23, if the value of the variable r is less than N(k), increase the value of r by 1 and go to S22; if the value of the variable r is equal to or greater than N(k), go to S25;

[0042] S24, perform co-solution adjustment on each pixel in the eight-neighborhood of p(k,r), and go to S23;

[0043] S25, end the adjustment.

[0044] Furthermore, in step S24, the method of co-solution adjustment for each pixel in the eight-neighborhood of p(k,r) is specifically as follows: let the eight-neighborhood of p(k,r) contain N(k,r) pixels, N(k,r) is a variable (the value interval of N(k,r) is [1,8]), and pon(k,r,t) represents the pixel value corresponding to the t-th pixel in the eight-neighborhood of p(k,r);

[0045] The co-solution algorithm is defined as follows: if the value of pon(k,r,t) is less than or equal to K1, or greater than or equal to K2, then the value of pon(k,r,t) is changed to max{pon(k,r,t),En(r)}*K0, where max{} means taking the maximum value of the number in {};

[0046] In the co-solution algorithm, t is traversed from t=1 to t=N(k,r), thereby completing the pixel value change of pon(k,r,1),pon(k,r,2),…,pon(k,r,N(k,r));

[0047] Among them, K1=Ecv-Ecv*K0, K2=Ecv+Ecv*K0, K0=(MO1-MO2) / MO1, MO1 represents the minimum pixel value of all pixels in the eight-neighborhood of p(k,r), and MO2 represents the maximum pixel value of all pixels in the eight-neighborhood of p(k,r).

[0048] The beneficial effect of this step is: by judging whether the pixel value in the neighborhood is within the stable interval [K1, K2], the pixel details of the image can be emphasized to different degrees in different areas, thereby achieving an improvement in the detail richness of the overall image. The reason for using K1 and K2 as the criteria for judging whether the pixel value needs to be adjusted is that if pixel jumps occur in a smaller local area (such as the eight-neighborhood) (that is, the pixel values ​​corresponding to continuous pixels are unstable, and the difference between the before and after values ​​is large), it means that these pixels are more important for displaying key information of the image and are often displayed as key features of vascular tissue. However, if the influence of neighboring pixels is not considered and the pixel values ​​of all pixels are changed globally, the loss of image details and the degradation of the overall visual effect will be caused. Therefore, using K1 and K2 as the interval judgment criteria for pixels can avoid over-smoothing while maintaining the consistency of key pixels in the image in details, making the image information of vascular tissue more prominent and improving the information value of the image.

[0049] The present invention also provides a rapid identification imaging system for an abnormal oral blood vessel area. The rapid identification imaging system for an abnormal oral blood vessel area comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in a rapid identification imaging method for an abnormal oral blood vessel area are implemented. The rapid identification imaging system for an abnormal oral blood vessel area can be run in computing devices such as desktop computers, notebook computers, mobile phones, cell phones, tablet computers, PDAs, and cloud data centers. The executable system may include, but is not limited to, a processor, a memory, and a server cluster. The processor executes the computer program in the following system units:

[0050] An image scanning unit, used for performing imaging scanning on the oral region of the patient to obtain an initial image;

[0051] An extraction and division unit, used for performing foreground extraction and division on the initial image to obtain a plurality of foreground target areas;

[0052] A pixel calculation unit, used for calculating edge common solution values ​​according to pixel distribution of the initial image;

[0053] The pixel adjustment unit is used to adjust the pixels of the initial image by edge co-solution values ​​to obtain an output image.

[0054] The beneficial effects of the present invention are as follows: the method can effectively identify and highlight the pixel information of abnormal areas in oral blood vessels, and by extracting the foreground and analyzing the edge information of the sub-area, the initial image is adjusted in a local range, which can effectively enhance the details and pixel contrast of the abnormal area, and enhance the high recognition of vascular tissue while retaining the real information of the image. At the same time, the pixel processing method of each region can speed up the process of recognition imaging and improve the accuracy of image processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The above and other features of the present invention will become more obvious by describing in detail the embodiments shown in the accompanying drawings. The same reference numerals in the accompanying drawings of the present invention represent the same or similar elements. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other accompanying drawings can be obtained based on these accompanying drawings without creative work. In the accompanying drawings:

[0056] Figure 1 Shown is a flow chart of a rapid identification imaging method for oral vascular abnormality areas;

[0057] Figure 2 Shown is a system structure diagram of a rapid identification imaging system for oral vascular abnormal areas. DETAILED DESCRIPTION

[0058] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0059] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0060] like Figure 1 The flowchart of the method for rapid identification and imaging of oral vascular abnormality areas according to the present invention is shown below. Figure 1 A rapid identification and imaging method for abnormal oral blood vessels according to an embodiment of the present invention is described below.

[0061] The present invention provides a method for rapid identification and imaging of oral vascular abnormality areas, the method comprising the following steps:

[0062] Perform an imaging scan of the patient's oral region to obtain an initial image;

[0063] Extract and divide the foreground of the initial image to obtain multiple foreground target areas;

[0064] According to the pixel distribution of the initial image, the edge co-solution value is calculated;

[0065] The initial image is pixel-adjusted using the edge co-solution value to obtain the output image.

[0066] Furthermore, the method of imaging and scanning the oral area of ​​the patient to obtain the initial image is specifically: capturing and imaging the area inside the patient's oral cavity through an electronic fluorescence endoscope, or imaging and scanning the oral area of ​​the patient through an oral scanner to obtain a color initial image.

[0067] Furthermore, the method of performing foreground extraction and division on the initial image to obtain multiple foreground target areas is as follows: performing foreground extraction (or background separation) on the initial image through an edge detection algorithm or an image segmentation algorithm to obtain the foreground part of the initial image, recording the foreground part as a large area, and dividing the large area into M sub-areas (by dividing the sub-areas, block processing of the abnormal area of ​​the oral cavity is achieved to improve the processing speed and the quality and effect of the image generated after processing), and using these M areas as M foreground target areas (the foreground target areas are closed areas).

[0068] Preferably, the value of M is set to 20.

[0069] Specifically, the large region is divided into M sub-regions by a division method using a region growing algorithm or a region splitting and merging algorithm.

[0070] Furthermore, the edge co-solution value is calculated according to the pixel distribution of the initial image, wherein the method for obtaining the pixel distribution of the initial image is specifically as follows: fgd(j) represents the j-th foreground target area among M foreground target areas, j is a serial number, and the value range of j is j=1, 2, …, M; all boundary pixels of fgd(j) are screened out in the initial image, and the sum of the pixel values ​​of all boundary pixels of fgd(j) is recorded as Mf(j), then the M foreground target areas fgd(1), fgd(2), …, fgd(M) correspond to M values ​​Mf(1), Mf(2), …, Mf (M).

[0071] Specifically, according to the pixel distribution of the initial image, the method for calculating the edge co-solution value is:

[0072] Create a blank array Mf[], add M values ​​Mf(1), Mf(2), …, Mf (M) to the array Mf[] in sequence, then the j-th value in the array Mf[] is represented as Mf(j);

[0073] Subtract the minimum value in the array Mf[] from the M values ​​in the array Mf[] to obtain M first values, negate the M first values, and exponentially perform the M first values ​​after negation with the natural constant e as the base to obtain M second values, multiply the M second values ​​with the M values ​​in the array Mf[] in sequence to obtain M third values, divide the maximum value in the array Mf[] by the M third values ​​in sequence to obtain M fourth values, accumulate the M fourth values, and record the value obtained after accumulation as the edge common solution value Ecv;

[0074] Its mathematical expression is:

[0075] ;

[0076] Where MxMf represents the maximum value in the array Mf[], and MnMf represents the minimum value in the array Mf[].

[0077] Furthermore, all boundary pixels of fgd(j) are screened out in the initial image, wherein all boundary pixels refer to all pixels constituting the boundary of fgd(j) (or all pixels located in the outermost layer of fgd(j)).

[0078] Specifically, the method of adjusting the pixels of the initial image by edge co-solution value to obtain the output image is:

[0079] S1, set variable k = 1, the value range of variable k is the same as the value range of j, and go to S2;

[0080] S2, let fgd(k) contain N(k) pixels, N(k) is a variable, each pixel corresponds to a pixel value, and the pixel values ​​of these N(k) pixels are adjusted in turn, and then go to S3; fgd(k) represents the kth foreground target area corresponding to the value of variable k among the M foreground target areas;

[0081] S3, if the value of variable k is less than M, then increase the value of k by 1 (increment k to enter the next foreground target area), and go to S2; if the value of variable k is greater than or equal to M (when k=M, it means that the pixels in the M foreground target areas have been adjusted and the traversal is completed), then go to S4;

[0082] S4, saving the initial image after pixel adjustment as an output image, and outputting the output image to a display.

[0083] Furthermore, the method of sequentially adjusting the pixel values ​​of the N(k) pixels is specifically as follows:

[0084] S21, p(k,i) represents the i-th pixel among the N(k) pixels, i is the serial number, and the value range of i is i=1,2,…,N(k). Initialize a variable r, the value range of r is the same as the value range of i, and set the initial value of r to r=1 (use r as the serial number traversal variable to traverse and adjust N(k) pixels), and go to S22;

[0085] S22, record the average value of all pixels in the eight neighborhoods of p(k,r) as En(r), if the value of En(r) is less than Ecv, go to S23; if the value of En(r) is greater than or equal to Ecv, go to S24; p(k,r) represents the rth pixel corresponding to the value of variable r in N(k) pixels;

[0086] S23, if the value of the variable r is less than N(k), increase the value of r by 1 and go to S22; if the value of the variable r is equal to or greater than N(k), go to S25;

[0087] S24, perform co-solution adjustment on each pixel in the eight-neighborhood of p(k,r), and go to S23;

[0088] S25, end the adjustment.

[0089] The eight-neighborhood of p(k,r) (that is, the eight-neighborhood of a pixel) refers to the adjacent pixels above, below, left, right, and in the four diagonal directions surrounding p(k,r). The eight-neighborhood is usually eight pixels (inner points of the region), but for some corner points or boundary points, the eight-neighborhood is three pixels (corner points, which have no adjacent elements on both sides) or five pixels (boundary points, which have no adjacent elements on one side).

[0090] Further, in step S24, the method of co-solution adjustment for each pixel in the eight-neighborhood of p(k,r) is specifically as follows: let the eight-neighborhood of p(k,r) contain N(k,r) pixels, N(k,r) is a variable (the value range of N(k,r) is [1,8]), pon(k,r,t) represents the pixel value corresponding to the t-th pixel in the eight-neighborhood of p(k,r), t is a sequence number, and the value range of t is t=1,2,…,N(k,r);

[0091] The co-solution algorithm is defined as follows: if the value of pon(k,r,t) is less than or equal to K1, or greater than or equal to K2, then the value of pon(k,r,t) is changed to max{pon(k,r,t),En(r)}*K0, where max{} means taking the maximum value of the number in {};

[0092] In the co-solution algorithm, t is traversed from t=1 to t=N(k,r), thereby completing the pixel value change of pon(k,r,1),pon(k,r,2),…,pon(k,r,N(k,r));

[0093] Among them, K1=Ecv-Ecv*K0, K2=Ecv+Ecv*K0, K0=(MO1-MO2) / MO1, MO1 represents the minimum pixel value of all pixels in the eight-neighborhood of p(k,r), and MO2 represents the maximum pixel value of all pixels in the eight-neighborhood of p(k,r).

[0094] The rapid identification and imaging system for oral vascular abnormality areas comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned rapid identification and imaging method for oral vascular abnormality areas are implemented. The rapid identification and imaging system for oral vascular abnormality areas can be run on computing devices such as desktop computers, notebook computers, mobile phones, cell phones, tablet computers, PDAs, and cloud data centers. The executable systems may include, but are not limited to, processors, memories, and server clusters.

[0095] An embodiment of the present invention provides a rapid identification imaging system for oral vascular abnormality areas, such as Figure 2 As shown, a rapid identification imaging system for oral vascular abnormality areas of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the rapid identification imaging method for oral vascular abnormality areas are implemented. The processor executes the computer program to run in the following system units:

[0096] An image scanning unit, used for performing imaging scanning on the oral region of the patient to obtain an initial image;

[0097] An extraction and division unit, used for performing foreground extraction and division on the initial image to obtain a plurality of foreground target areas;

[0098] A pixel calculation unit, used for calculating edge common solution values ​​according to pixel distribution of the initial image;

[0099] The pixel adjustment unit is used to adjust the pixels of the initial image by edge co-solution values ​​to obtain an output image.

[0100] The rapid identification and imaging system of the oral vascular abnormality area can be run in computing devices such as desktop computers, laptop computers, PDAs, and cloud data centers. The rapid identification and imaging system of the oral vascular abnormality area includes, but is not limited to, a processor and a memory. Those skilled in the art can understand that the example is only an example of a rapid identification and imaging method and system of the oral vascular abnormality area, and does not constitute a limitation of a rapid identification and imaging method and system of the oral vascular abnormality area, and may include more or fewer components than the example, or a combination of certain components, or different components. For example, the rapid identification and imaging system of the oral vascular abnormality area may also include input and output devices, network access devices, buses, etc.

[0101] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete component gate circuits or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the oral vascular abnormality area rapid identification imaging system, and uses various interfaces and lines to connect the various sub-regions of the entire oral vascular abnormality area rapid identification imaging system.

[0102] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the method and system for rapid identification and imaging of oral vascular abnormality areas by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0103] The present invention provides a method and system for rapid identification and imaging of abnormal areas of oral blood vessels. The patient's oral area is imaged and scanned to obtain an initial image. The initial image is subjected to foreground extraction and division to obtain multiple foreground target areas. According to the pixel distribution of the initial image, the edge co-solution value is calculated. The initial image is pixel-adjusted by the edge co-solution value to obtain an output image. The method can effectively identify and highlight the pixel information of the abnormal area in the oral blood vessels. By foreground extraction and analyzing the edge information of the sub-area, the initial image is pixel-adjusted in a local range, which can effectively enhance the details and pixel contrast of the abnormal area, while retaining the real information of the image, enhancing the high recognition of the vascular tissue, and by using the pixel processing method of the sub-area, the identification imaging process can be accelerated and the accuracy of the image processing can be improved. Although the description of the present invention has been quite detailed and several embodiments are described in particular, it is not intended to be limited to any of these details or embodiments or any special embodiments, so as to effectively cover the predetermined scope of the present invention. In addition, the above description of the present invention is based on the embodiments foreseeable by the inventor, and its purpose is to provide a useful description, and those non-substantial changes to the present invention that have not yet been foreseen can still represent equivalent changes to the present invention.

Claims

1. A method for rapid identification and imaging of abnormal oral vascular areas, characterized in that: The method comprises the following steps: Perform an imaging scan of the patient's oral region to obtain an initial image; Extract and divide the foreground of the initial image to obtain multiple foreground target areas; According to the pixel distribution of the initial image, the edge co-solution value is calculated; The initial image is pixel-adjusted by edge co-solution values ​​to obtain an output image; The method for obtaining the pixel distribution of the initial image is as follows: fgd(j) represents the jth foreground target area among M foreground target areas, all boundary pixels of fgd(j) are screened out in the initial image, and the sum of the pixel values ​​of all boundary pixels of fgd(j) is recorded as Mf(j), then the M foreground target areas fgd(1), fgd(2), ..., fgd(M) correspond to M values ​​Mf(1), Mf(2), ..., Mf (M); According to the pixel distribution of the initial image, the method for calculating the edge co-solution value is: Create a blank array Mf[], add M values ​​Mf(1), Mf(2), …, Mf(M) to the array Mf[] in sequence, then the j-th value in the array Mf[] is represented as Mf(j); Subtract the minimum value in array Mf[] from the M values ​​in array Mf[] to obtain M first values, negate the M first values, and exponentially perform the exponential operation on the M first values ​​after negation with the natural constant e to obtain M second values, multiply the M second values ​​with the M values ​​in array Mf[] in sequence to obtain M third values, divide the maximum value in array Mf[] by the M third values ​​in sequence to obtain M fourth values, add up the M fourth values, and record the value obtained after addition as the marginal common solution value Ecv.

2. The method for rapid identification and imaging of oral vascular abnormality areas according to claim 1, characterized in that: The area inside the patient's oral cavity is captured and imaged by an electronic fluorescence endoscope, or the area inside the patient's oral cavity is imaged and scanned by an oral scanner to obtain a color initial image.

3. The method for rapid identification and imaging of oral vascular abnormality areas according to claim 1, characterized in that: The method for extracting and dividing the foreground of the initial image to obtain multiple foreground target areas is as follows: extracting the foreground of the initial image by an edge detection algorithm or an image segmentation algorithm to obtain the foreground part of the initial image, recording the foreground part as a large area, dividing the large area into M sub-areas, and using the M areas as M foreground target areas.

4. The method for rapid identification and imaging of oral vascular abnormality areas according to claim 3, characterized in that: The edge detection algorithm is a Sobel edge detection algorithm, and the image segmentation algorithm is a region growing algorithm.

5. The method for rapid identification and imaging of oral vascular abnormality areas according to claim 3, characterized in that: The foreground of the initial image is extracted using the GrabCut algorithm.

6. The method for rapid identification and imaging of oral vascular abnormality areas according to claim 1, characterized in that: The method of adjusting pixels of the initial image by edge co-solution value to obtain the output image is specifically as follows: sharpening all pixels in the initial image by unsharp masking method, saving the sharpened initial image as the output image, and outputting the output image to a display; wherein, in the unsharp masking method, the specific value of the parameter sharpening amount is set to the edge co-solution value.

7. A rapid identification imaging system for abnormal oral vascular areas, characterized in that: The rapid identification and imaging system for oral vascular abnormality areas comprises: a processor, a memory, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the rapid identification and imaging method for oral vascular abnormality areas described in any one of claims 1 to 6 are implemented. The rapid identification and imaging system for oral vascular abnormality areas runs in a computing device such as a laptop computer, a PDA, or a cloud data center.

Images