Deformity area identification method for paranasal sinus image under nasal endoscope

Abstract

The invention relates to the field of paranasal sinus image anomaly identification, in particular to a method for identifying an abnormal area of a paranasal sinus image under a nasal endoscope. The method comprises the following steps: segmenting a paranasal sinus image to obtain a gray surface region, and obtaining an edge curve in the gray surface region; obtaining an inflection point in the curve, fitting an inflection point curve, obtaining a curve difference coefficient through the shape difference between the inflection point curve and the inflection point curve, and further obtaining an accumulated curve difference coefficient of each image; all the images are clustered by using the image clustering algorithm to obtain paranasal sinus image clusters, and the paranasal sinus image clusters are sorted; obtaining the specific coefficient of each cluster according to the difference of the accumulated curve difference coefficients between different clusters; screening the clusters to obtain paranasal sinus image abnormal clusters; and identifying the abnormal region according to the abnormal cluster. According to the method, all paranasal sinus malformation areas can be accurately identified, so that related medical personnel can accurately judge abnormal conditions in paranasal sinus images.

Description

Technical Field

[0001] The present invention relates to the field of abnormality recognition of sinus images, and in particular to a method for marking deformed areas of sinus images under nasal endoscopy. Background Art

[0002] Nasal endoscopy is a common clinical diagnostic method, mainly used to examine lesions of the nasal cavity and paranasal sinuses. However, traditional manual diagnostic methods are highly subjective, inefficient, and prone to missing lesions in the clinical stage. With the development of relevant computer technology, image processing technology, especially the automatic identification method of deformed areas based on computer vision, can greatly improve the accuracy and efficiency of diagnosis. The present invention proposes an innovative image processing method that uses computer vision technology to identify deformed areas in nasal endoscopy images, assisting doctors in making relevant clinical diagnoses efficiently and accurately.

[0003] Nasal endoscopy is a common clinical diagnostic method, mainly used to examine lesions of the nasal cavity and sinuses. However, traditional manual diagnostic methods are highly subjective, inefficient, and prone to missing lesions in the clinical stage. They are unable to accurately identify deformed areas in sinus images, ultimately resulting in the inability of relevant medical personnel to accurately judge abnormalities in sinus images. Summary of the invention

[0004] In order to solve the problem that the traditional method for diagnosing sinus deformity areas is highly subjective, inefficient and easy to miss the lesion area in the clinical stage, and cannot accurately mark the deformity area in the sinus image, which ultimately leads to the technical problem that the relevant medical personnel cannot accurately judge the abnormal situation in the sinus image, the purpose of the present invention is to provide a method for marking the deformity area of ​​the sinus image under nasal endoscopy, and the technical scheme adopted is as follows: A method for identifying deformed areas of sinus images under nasal endoscopy, the method comprising: Acquire a preset number of sinus images and the acquisition time node of each sinus image; Segment each sinus image according to a clustering algorithm to obtain a gray surface area in each sinus image; perform edge detection on the gray surface area to obtain all edge curves of the gray surface area; obtain all inflection points of each edge curve; obtain the corresponding inflection point curve of each edge curve according to the distribution characteristics of all inflection points of each edge curve; obtain the curve difference coefficient between each edge curve and the inflection point curve according to the shape difference between each edge curve and the inflection point curve; accumulate all curve difference coefficients in the gray surface area of ​​each sinus image to obtain the accumulated curve difference coefficient of each sinus image; cluster a preset number of sinus images using the accumulated curve difference coefficient to obtain clusters of all sinus images; sort the sinus image clusters according to the acquisition time node of each sinus image in each sinus image cluster; Select any one of the sinus image clusters as a reference cluster; obtain the specific coefficient of the reference cluster according to the difference in cumulative curve difference coefficients between the sinus images in the reference cluster and the sinus images in other sinus image clusters; screen all the sinus image clusters according to the specific coefficient to obtain the abnormal sinus image cluster; and identify the deformed area of ​​the sinus image according to the abnormal sinus image cluster.

[0005] Furthermore, the method for obtaining the gray surface area includes: Clustering each of the sinus images according to the grayscale value of the pixels to obtain three pixel clusters; Sort the three pixel clusters from large to small according to the mean grayscale values ​​of the pixels, and use the second pixel cluster as the gray surface cluster; The area where the pixel points corresponding to the gray surface cluster are located is used as the gray surface area in the sinus image.

[0006] Furthermore, a method for obtaining the inflection point curve corresponding to each edge curve includes: The Newton interpolation method is used to perform curve fitting on the inflection point in each edge curve to obtain the corresponding inflection point curve of each edge curve, and the inflection point curve corresponds to the starting end point and the ending end point of the edge curve one by one.

[0007] Furthermore, the method for obtaining the curve difference coefficient includes: Constructing a Cartesian coordinate system for the edge curve and the inflection point curve, and obtaining the edge curve ordinate and the inflection point curve ordinate of each abscissa; The difference between the ordinate of the edge curve corresponding to each horizontal coordinate and the ordinate of the inflection point curve corresponding to each horizontal coordinate is calculated as the first difference; the first differences of all horizontal coordinates are accumulated and summed to obtain the curve difference coefficient between each edge curve and the inflection point curve.

[0008] Further, the sinus image clusters are sorted according to the acquisition time node of each sinus image in each sinus image cluster, including: Counting the start time node and the end time node of the sinus images of the maximum number of adjacent time nodes in each sinus image cluster, and taking the time between the end time node and the start time node as the timestamp of each sinus image cluster; Each sinus image cluster is sorted according to the timestamp to obtain the sequential arrangement of all sinus image clusters.

[0009] Furthermore, the method for obtaining the specific coefficient includes: The specific coefficient is obtained according to the specific coefficient calculation formula, and the specific coefficient calculation formula is as follows: In the formula, represents the specificity coefficient of the reference cluster; represents the number of sinus images in the reference cluster; Indicates the first The coefficient of difference of the cumulative curves of the sinus images; represents the number of clusters of sinus images; It represents the mean value of the cumulative curve difference coefficient of sinus images in other sinus image clusters except the reference cluster; represents the mean value of the coefficient of difference of the cumulative curves of the sinus images in the previous sinus image cluster of the reference cluster; represents the mean of the coefficient of difference of the cumulative curves of the sinus images in the next sinus image cluster of the reference cluster; It represents the maximum value of the cumulative curve difference coefficient of all sinus images in the reference cluster; Represents Iverson brackets, where if the condition in the brackets is met, the value in the brackets is 1, and if the condition in the brackets is not met, the value in the brackets is 0.

[0010] Furthermore, the method for acquiring abnormal clusters of sinus images includes: The sinus image clusters whose specific coefficients are greater than a preset first threshold are clustered as sinus image abnormality clusters.

[0011] A system for identifying deformed areas of sinus images under nasal endoscopy, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for identifying deformed areas of sinus images under nasal endoscopy when executing the computer program.

[0012] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for identifying deformed areas of sinus images under nasal endoscopy are implemented.

[0013] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for identifying deformed areas of sinus images under nasal endoscopy are implemented.

[0014] The present invention has the following beneficial effects: The present invention first obtains the sinus image and the acquisition time node of each sinus image, so as to analyze the process of collecting images with the nasal endoscope; when the light on the head of the nasal endoscope illuminates the sinus area, there will be obvious overexposure close to the light and too dark away from the light, and the areas corresponding to the bright and dark surfaces will have extreme cases of overexposure and too dark, so the present invention selects the gray surface area; since the edge curvature of the image area corresponding to the deformed area changes greatly, the gray surface area is edge detected to obtain all edge curves of the gray surface area; since the inflection point is the position where the direction changes significantly in the sinus image, all inflection points of each edge curve are obtained; curve fitting is performed on the inflection point on each edge curve to obtain the inflection point curve, and by comparing the shape between the inflection point curve and the edge curve, it can be analyzed whether there is an obvious curvature change at the edge; since the inflection point curve is different from the actual edge curve The larger the value is, the greater the curvature change of the edge pixel point on the edge curve is, so the curve difference coefficient between each edge curve and the inflection point curve is analyzed; since there are multiple edge curves and corresponding inflection point curves in the gray surface area of ​​the sinus image, multiple curve difference coefficients can be obtained, so all curve difference coefficients in the gray surface area of ​​the sinus image are accumulated to obtain the accumulated curve difference coefficient of each sinus image; the accumulated curve difference coefficient is used to cluster a preset number of sinus images to obtain all sinus image clusters; in multiple sinus image clusters, the larger the accumulated curve difference coefficient in the sinus images in the cluster, the more abnormal the sinus image cluster is, and the more likely the sinus images in the cluster are obtained by shooting through the deformed area, so the specific coefficient of the sinus image cluster is analyzed; the specific coefficient is used to screen out the abnormal clusters of the sinus images; the deformed area of ​​the sinus image is marked according to the abnormal clusters of the sinus images. The present invention can accurately mark all sinus deformity areas, so that relevant medical personnel can accurately judge the abnormal conditions in the sinus images. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flow chart of a method for identifying deformed areas of sinus images under nasal endoscopy provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the method for identifying the deformed area of ​​the sinus image under nasal endoscopy proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The following is a detailed description of a method for marking deformed areas of sinus images under nasal endoscopy provided by the present invention in conjunction with the accompanying drawings.

[0020] See also Figure 1 , which shows a method for identifying deformed areas of sinus images under nasal endoscopy provided by an embodiment of the present invention, the method comprising: Step S1: obtaining a preset number of sinus images and the time point at which each sinus image is obtained.

[0021] The embodiment of the present invention is mainly used in the scene of identifying the deformed area in the sinus image, so the sinus image is first obtained. In actual situations, when using a nasal endoscope to collect images, a slender endoscopic instrument is inserted through the patient's nasal cavity, and a local image of the sinus area is displayed in real time with the help of a high-resolution camera. The endoscope usually has an adjustable light source and provides a clear field of view through the lens. During the exploration process, the image information will be transmitted to the display screen in real time. In one embodiment of the present invention, a sinus image is collected every 200ms, and the preset number is set to 20. It should be noted that in other embodiments of the present invention, the time node and the preset number of collection can be set by yourself, and are not limited here.

[0022] In one embodiment of the present invention, the collected sinus image is grayed and denoised to obtain the final sinus image for the following steps. It should be noted that graying and denoising are both well-known technical means to those skilled in the art and will not be described in detail here.

[0023] Step S2: segment each sinus image according to the clustering algorithm to obtain the gray surface area in each sinus image; perform edge detection on the gray surface area to obtain all edge curves of the gray surface area; obtain all inflection points of each edge curve; obtain the corresponding inflection point curve of each edge curve according to the distribution characteristics of all inflection points of each edge curve; obtain the curve difference coefficient between each edge curve and the inflection point curve according to the shape difference between each edge curve and the inflection point curve; accumulate all the curve difference coefficients in the gray surface area of ​​each sinus image to obtain the accumulated curve difference coefficient of each sinus image; cluster a preset number of sinus images using the accumulated curve difference coefficient to obtain all sinus image clusters; sort the sinus image clusters according to the acquisition time node of each sinus image in each sinus image cluster.

[0024] In actual situations, as the nasal endoscope moves continuously, the sinus area will change from bright to dark, and the originally dark area will become brighter. In addition, the nasal endoscope requires a very small space around it when exploring the sinus area. Therefore, when the sinus area is illuminated by the light on the head of the nasal endoscope, there will be obvious overexposure close to the light and too dark away from the light. Therefore, the sinus image is segmented into areas corresponding to the bright side, the gray side and the dark side, among which the areas corresponding to the bright side and the dark side may be overexposed and too dark. Therefore, in the embodiment of the present invention, the gray side area is selected to perform the following steps. Since the grayscale value difference between the gray side area and the bright side area and the dark side area is large, in the embodiment of the present invention, each sinus image is segmented according to the clustering algorithm to obtain the gray side area in each sinus image.

[0025] In one embodiment of the present invention, a K-means clustering algorithm is used to cluster each sinus image. It should be noted that other clustering algorithms, such as a hierarchical clustering algorithm, may also be used in other embodiments of the present invention. The clustering algorithm is a technical means well known to those skilled in the art and will not be limited or elaborated herein.

[0026] Preferably, in one embodiment of the present invention, the method for obtaining the gray surface area includes: Each sinus image is clustered according to the grayscale value of the pixels to obtain three pixel clusters; the three pixel clusters are sorted from large to small according to the grayscale mean of the pixels, and the second pixel cluster is used as the gray surface cluster; the area where the pixels corresponding to the gray surface cluster are located is used as the gray surface area in the sinus image.

[0027] Due to the abnormality in the sinus area, the sinus image shows that the edge curvature of the image area corresponding to the deformed area changes significantly. Combined with the moderate grayscale change in the gray surface area mentioned in the above process, the area has a convex change, which can make the illuminated shadow of the convex appear in the image and will not be covered by the overexposed or dark area. Therefore, in this embodiment of the present invention, edge detection is performed on the gray surface area to obtain all edge curves of the gray surface area.

[0028] In the edge curve, the inflection point is the position where the direction of the sinus image changes significantly, which often appears on the edge of the sinus image and is often used as a key feature in the sinus image to participate in the segmentation process in the gray area of ​​the sinus image. Therefore, in the embodiment of the present invention, all inflection points of each edge curve are obtained. It should be noted that the method of obtaining the inflection point is a technical means well known to those skilled in the art and will not be described in detail here.

[0029] Curve fitting is performed on the inflection point on each edge curve to obtain the inflection point curve. By comparing the shape of the inflection point curve with the edge curve, it is possible to analyze whether there is an obvious curvature change on the edge. Therefore, in the embodiment of the present invention, the corresponding inflection point curve of each edge curve is obtained based on the distribution characteristics of all inflection points of each edge curve.

[0030] Preferably, in one embodiment of the present invention, a method for obtaining the inflection point curve corresponding to each edge curve includes: The Newton interpolation method is used to perform curve fitting on the inflection points in each edge curve to obtain the corresponding inflection point curve of each edge curve, and the inflection point curve corresponds to the starting endpoint and the ending endpoint of the edge curve one by one. It should be noted that in other embodiments of the present invention, other curve fitting methods such as the least squares method can also be used to obtain the inflection point curve, and the above curve fitting methods are all technical means well known to those skilled in the art, and are not limited or elaborated herein.

[0031] Since the greater the difference between the inflection point curve and the actual edge curve, it means that the edge pixel points on the edge curve have a larger curvature change or irregularity, and the curvature change can identify the contour and shape of the sinus area. The greater the curvature change, the more drastic the change in the contour and shape of the sinus area, and the more likely it is that a deformed area will appear in the sinus area. Therefore, in the embodiment of the present invention, the curve difference coefficient between each edge curve and the inflection point curve is obtained according to the shape difference between each edge curve and the inflection point curve.

[0032] Preferably, in one embodiment of the present invention, the method for obtaining the curve difference coefficient includes: A Cartesian coordinate system is constructed for the edge curve and the inflection point curve. Since the above process has mentioned that the starting endpoints and the ending endpoints of the edge curve and the inflection point curve correspond one to one, the horizontal coordinates of all pixel points on the edge curve and the inflection point curve correspond one to one, and the corresponding vertical coordinates of the edge curve and the inflection point curve are obtained for each horizontal coordinate.

[0033] The difference between the ordinate of the corresponding edge curve of each horizontal coordinate and the ordinate of the corresponding inflection point curve is calculated as the first difference; the first differences of all horizontal coordinates are accumulated and summed to obtain the curve difference coefficient between each edge curve and the inflection point curve, wherein the larger the curve difference coefficient, the greater the difference between the edge curve and the corresponding inflection point curve, and the more drastic the change of the edge curve.

[0034] Since there are multiple edge curves and corresponding inflection point curves in the gray surface area of ​​the sinus image, multiple curve difference coefficients can be obtained, so all curve difference coefficients in the gray surface area of ​​the sinus image are accumulated to obtain the accumulated curve difference coefficient of each sinus image. The accumulated curve difference coefficient is used to judge whether the edge of each sinus image changes drastically, and participates in subsequent operation steps.

[0035] If there is a deformed area in the sinus image, the cumulative curve difference coefficient is large, and if there is no deformed area in the sinus image, the cumulative curve difference coefficient is small, and there is a large difference between the two. Therefore, in an embodiment of the present invention, a preset number of sinus images are clustered using the cumulative curve difference coefficient to obtain all sinus image clusters, wherein the degree of change of the edges within the same sinus image clusters is similar. It should be noted that in one embodiment of the present invention, a K-means clustering algorithm is used to cluster a preset number of sinus images to obtain all sinus image clusters. The K-means clustering algorithm is a technical means well known to those skilled in the art and is not limited or elaborated herein.

[0036] Since the sinus image clusters are clustered according to the cumulative curve difference coefficient, the sinus images in the same cluster may not be adjacent at the acquisition time node, so in the embodiment of the present invention, the sinus image clusters are sorted.

[0037] Preferably, in one embodiment of the present invention, the sinus image clusters are sorted according to the acquisition time node of each sinus image in each sinus image cluster, including: Since the difference in the time nodes of adjacent sinus images is very small, there are multiple adjacent sinus images with similar cumulative curve difference coefficients, so most of the sinus images in the same cluster are adjacent in the acquisition time nodes. Therefore, the start time node and the end time node of the sinus images of the maximum number of adjacent time nodes in each sinus image cluster are counted, and the time between the end time node and the start time node is used as the timestamp of each sinus image cluster; Each sinus image cluster is sorted according to the timestamp to obtain the sequential arrangement of all sinus image clusters.

[0038] Step S3: Select any sinus image cluster as a reference cluster; obtain the specific coefficient of the reference cluster according to the difference in the cumulative curve difference coefficient between the sinus images in the reference cluster and the sinus images in other sinus image clusters; screen all sinus image clusters according to the specific coefficient to obtain abnormal sinus image clusters; and identify the deformed area of ​​the sinus image according to the abnormal sinus image cluster.

[0039] In multiple sinus image clusters, the larger the cumulative curve difference coefficient of the sinus images in the cluster is, the more abnormal the sinus image cluster is, and the more likely the sinus images in the cluster are obtained by photographing the deformed area. Therefore, in the embodiment of the present invention, the specific coefficient of the reference cluster is obtained based on the difference in the cumulative curve difference coefficient between the sinus images in the reference cluster and the sinus images in other sinus image clusters.

[0040] Preferably, in one embodiment of the present invention, the method for obtaining the specific coefficient includes: The specific coefficient is obtained according to the specific coefficient calculation formula, which is as follows: In the formula, represents the specificity coefficient of the reference cluster; represents the number of sinus images in the reference cluster; Indicates the first The coefficient of difference of the cumulative curves of the sinus images; represents the number of clusters of sinus images; It represents the mean value of the cumulative curve difference coefficient of sinus images in other sinus image clusters except the reference cluster; represents the mean value of the coefficient of difference of the cumulative curves of the sinus images in the previous sinus image cluster of the reference cluster; represents the mean of the coefficient of difference of the cumulative curves of the sinus images in the next sinus image cluster of the reference cluster; It represents the maximum value of the cumulative curve difference coefficient of all sinus images in the reference cluster; Represents Iverson brackets, where if the condition in the brackets is met, the value in the brackets is 1, and if the condition in the brackets is not met, the value in the brackets is 0.

[0041] In the specific coefficient calculation formula, the mean of the cumulative curve difference coefficient of the sinus images in the reference cluster is The mean difference coefficient of the cumulative curve with other sinus image clusters If the value is large, it means that the sinus images in the reference cluster are more abnormal. In this case, the sinus images in the reference cluster are further analyzed. Compared to The larger the value, the more abnormal the sinus images in the reference cluster are, and the larger the specific coefficient of the reference cluster is. The difference between the mean difference coefficient of the cumulative curve of the two adjacent sinus image clusters before and after the reference cluster and the mean difference coefficient of the cumulative curve of the reference cluster is The larger the value, the greater the change of the reference cluster compared with the adjacent sinus image cluster; the difference in the mean value of the cumulative curve difference coefficient of the two adjacent sinus image clusters before and after the reference cluster The smaller it is, the more obvious the abnormality of the sinus images of the reference cluster is, and the larger the specificity coefficient of the reference cluster is. At the same time, within the reference cluster, if the difference in the cumulative curve difference coefficient between the sinus images is smaller, it means that the sinus images within the reference cluster are generally abnormal, and the larger the specificity coefficient of the reference cluster is.

[0042] Preferably, in one embodiment of the present invention, the specific coefficient is normalized, and the sinus image clusters whose normalized specific coefficients are greater than a preset first threshold are clustered as sinus image abnormality clusters. In one embodiment of the present invention, the preset first threshold is set to 0.95. It should be noted that in other embodiments of the present invention, the preset first threshold is set voluntarily and is not limited here.

[0043] After screening out the abnormal sinus image cluster, all sinus images in the abnormal sinus image cluster are marked, among which all sinus images in the abnormal sinus image cluster can be used to assist in locating targets where deformities may exist. Relevant personnel can further observe and evaluate suspected deformity areas based on these images to determine their clinical significance and further diagnosis and treatment needs. It should be emphasized that this process is only an auxiliary tool for doctors. Automated screening and image labeling cannot replace the judgment of professional doctors. Doctors should combine clinical experience and other diagnostic methods to conduct a comprehensive assessment and diagnosis of deformity areas.

[0044] At this point, the identification of the deformed area of ​​the sinus image is completed.

[0045] In summary, a preset number of sinus images and the acquisition time node of each sinus image are obtained; each sinus image is segmented according to a clustering algorithm to obtain a gray surface area in each sinus image; edge detection is performed on the gray surface area to obtain all edge curves in the gray surface area; all inflection points of each edge curve are obtained; according to the distribution characteristics of all inflection points of each edge curve, the corresponding inflection point curve of each edge curve is obtained; according to the shape difference between each edge curve and the inflection point curve, the curve difference coefficient between each edge curve and the inflection point curve is obtained; all curve difference coefficients in the gray surface area of ​​each sinus image are accumulated to obtain each sinus image. The invention discloses a method for obtaining a plurality of sinus images of a plurality of different types of paranasal sinuses, and a method for obtaining a plurality of sinus images of a plurality of different types of paranasal sinuses. The method comprises the following steps: determining a cumulative curve difference coefficient of an image; clustering a preset number of sinus images using the cumulative curve difference coefficient to obtain all sinus image clusters; sorting the sinus image clusters according to the acquisition time node of each sinus image in each sinus image cluster; selecting any one of the sinus image clusters as a reference cluster; obtaining the specific coefficient of the reference cluster according to the difference in the cumulative curve difference coefficient between the sinus images in the reference cluster and the sinus images in other sinus image clusters; screening all the sinus image clusters according to the specific coefficient to obtain abnormal sinus image clusters; and marking the deformed areas of the sinus images according to the abnormal sinus image clusters.

[0046] An embodiment of the present invention provides a system for identifying deformed areas of sinus images under nasal endoscopy, the system comprising a memory, a processor and a computer program, wherein the memory is used to store the corresponding computer program, the processor is used to run the corresponding computer program, and when the computer program runs in the processor, it can implement the method described in steps S1-S3.

[0047] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0048] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for identifying deformed areas of sinus images under nasal endoscopy, characterized in that: The method comprises: Acquire a preset number of sinus images and the acquisition time node of each sinus image; Segment each sinus image according to a clustering algorithm to obtain a gray surface area in each sinus image; perform edge detection on the gray surface area to obtain all edge curves of the gray surface area; obtain all inflection points of each edge curve; obtain the corresponding inflection point curve of each edge curve according to the distribution characteristics of all inflection points of each edge curve; obtain the curve difference coefficient between each edge curve and the inflection point curve according to the shape difference between each edge curve and the inflection point curve; accumulate all curve difference coefficients in the gray surface area of ​​each sinus image to obtain the accumulated curve difference coefficient of each sinus image; cluster a preset number of sinus images using the accumulated curve difference coefficient to obtain clusters of all sinus images; sort the sinus image clusters according to the acquisition time node of each sinus image in each sinus image cluster; Select any one of the sinus image clusters as a reference cluster; obtain the specific coefficient of the reference cluster according to the difference in cumulative curve difference coefficients between the sinus images in the reference cluster and the sinus images in other sinus image clusters; screen all the sinus image clusters according to the specific coefficient to obtain the abnormal sinus image cluster; and identify the deformed area of ​​the sinus image according to the abnormal sinus image cluster.

2. The method for identifying deformed areas of sinus images under nasal endoscopy according to claim 1, characterized in that: The method for obtaining the gray surface area includes: Clustering each of the sinus images according to the grayscale value of the pixels to obtain three pixel clusters; Sort the three pixel clusters from large to small according to the mean grayscale values ​​of the pixels, and use the second pixel cluster as the gray surface cluster; The area where the pixel points corresponding to the gray surface cluster are located is used as the gray surface area in the sinus image.

3. The method for identifying deformed areas of sinus images under nasal endoscopy according to claim 1, characterized in that: The method for obtaining the inflection point curve corresponding to each edge curve includes: The Newton interpolation method is used to perform curve fitting on the inflection point in each edge curve to obtain the corresponding inflection point curve of each edge curve, and the inflection point curve corresponds to the starting end point and the ending end point of the edge curve one by one.

4. The method for identifying deformed areas of sinus images under nasal endoscopy according to claim 1, characterized in that: The method for obtaining the curve difference coefficient includes: Constructing a Cartesian coordinate system for the edge curve and the inflection point curve, and obtaining the edge curve ordinate and the inflection point curve ordinate of each abscissa; The difference between the ordinate of the edge curve corresponding to each horizontal coordinate and the ordinate of the inflection point curve corresponding to each horizontal coordinate is calculated as the first difference; the first differences of all horizontal coordinates are accumulated and summed to obtain the curve difference coefficient between each edge curve and the inflection point curve.

5. The method for identifying deformed areas of sinus images under nasal endoscopy according to claim 1, characterized in that: Sorting the sinus image clusters according to the acquisition time node of each sinus image in each sinus image cluster, including: Counting the start time node and the end time node of the sinus images of the maximum number of adjacent time nodes in each sinus image cluster, and taking the time between the end time node and the start time node as the timestamp of each sinus image cluster; Each sinus image cluster is sorted according to the timestamp to obtain the sequential arrangement of all sinus image clusters.

6. The method for identifying deformed areas of sinus images under nasal endoscopy according to claim 1, characterized in that: The method for obtaining the specific coefficient includes: The specific coefficient is obtained according to the specific coefficient calculation formula, and the specific coefficient calculation formula is as follows: In the formula, represents the specificity coefficient of the reference cluster; represents the number of sinus images in the reference cluster; Indicates the first The coefficient of difference of the cumulative curve of the sinus images; represents the number of clusters of sinus images; It represents the mean value of the cumulative curve difference coefficient of sinus images in other sinus image clusters except the reference cluster; represents the mean value of the coefficient of difference of the cumulative curves of the sinus images in the previous sinus image cluster of the reference cluster; represents the mean of the coefficient of difference of the cumulative curves of the sinus images in the next sinus image cluster of the reference cluster; It represents the maximum value of the cumulative curve difference coefficient of all sinus images in the reference cluster; Represents Iverson brackets, where if the condition in the brackets is met, the value in the brackets is 1, and if the condition in the brackets is not met, the value in the brackets is 0.

7. The method for identifying deformed areas of sinus images under nasal endoscopy according to claim 1, characterized in that: The method for acquiring abnormal clusters of sinus images comprises: The sinus image clusters whose specific coefficients are greater than a preset first threshold are clustered as sinus image abnormality clusters.

8. A system for identifying deformed areas of sinus images under nasal endoscopy, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for identifying deformed areas of sinus images under nasal endoscopy as described in any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for identifying deformed areas of sinus images under nasal endoscopy as described in any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for identifying deformed areas of sinus images under nasal endoscopy as described in any one of claims 1 to 7 are implemented.

Images