Vital sign data processing system for digestive endoscopy patient

Abstract

The invention relates to the technical field of denoising of gastrointestinal images of patients, in particular to a vital sign data processing system for digestive endoscopy of patients. A patient's gastrointestinal image is acquired. And randomly selecting one pixel in each image as a reference point, and calculating the noise influence degree of the reference point according to the difference between the neighborhood gradient distribution and the total image gradient distribution and the pixel gray scale difference in the neighborhood. And screening all to-be-denoised pixel points in the image. And for each to-be-denoised point, screening out a repair pixel point according to the noise influence degree in a preset window of the to-be-denoised point. And correcting the initial gray value of the target point by combining the gray difference between the target point and the repairing points and the noise influence degree difference to obtain a final gray value, and further obtaining a denoised gastrointestinal image. According to the invention, the noise influence in the gastrointestinal image of the patient can be removed as much as possible, so that the image capable of accurately identifying disease source features is obtained.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of patient gastrointestinal image denoising, and in particular to a vital sign data processing system for patients undergoing digestive endoscopy. BACKGROUND

[0002] Digestive endoscopy (including gastroscopy, colonoscopy, etc.) is mainly used for direct observation of the internal structure of the digestive tract, diagnosis and treatment of various digestive system diseases. Its examination purposes cover a variety of lesions from inflammation, ulcers to tumors. The patient-related image vital sign data processing system obtained through digestive endoscopy is evolving from "single parameter monitoring" to "AI-driven intelligent early warning closed loop". In the short term, it is necessary to break through the bottleneck of data integration and standardization, in the medium term, to rely on domestic substitution (hardware + AI algorithm) and sinking to the grassroots, and in the long term, to rely on the coordinated innovation of policy and technology. The industry opportunities and challenges coexist, and the clinical value is clear, which is a key growth point for medical informatization and precise anesthesia management.

[0003] When a patient is examined by a digestive endoscope, noise will inevitably be generated due to various reasons. At this time, the stomach image and intestinal image data obtained by the digestive endoscope become blurred due to the interference of noise. In the prior art, all pixel points affected by noise cannot be accurately removed, so that the disease source characteristics cannot be accurately identified. SUMMARY

[0004] In order to solve the technical problem that the stomach image and intestinal image data obtained by the digestive endoscope become blurred due to the interference of noise, and in the prior art, all pixel points affected by noise cannot be accurately removed, so that the disease source characteristics cannot be accurately identified, the purpose of the present application is to provide a vital sign data processing system for patients undergoing digestive endoscopy, and the technical solution adopted is as follows:

[0005] A vital sign data processing system for patients undergoing digestive endoscopy, the system comprises:

[0006] An image acquisition module for acquiring a stomach image and an intestinal image of a patient, wherein the stomach image and the intestinal image are collectively referred to as patient gastrointestinal images.

[0007] The pixel repairing module is configured to: select an optional pixel in each patient gastrointestinal image as a reference pixel; obtain a noise influence degree of the reference pixel according to a difference between a gradient distribution in a preset neighborhood of the reference pixel and a gradient distribution in each patient gastrointestinal image, and a gray difference between the reference pixel and other pixels in the preset neighborhood; select a to-be-de-noised pixel in each patient gastrointestinal image according to the noise influence degrees of all the pixels in each patient gastrointestinal image; select an optional to-be-de-noised pixel as a target pixel; select a repairing pixel in a preset window of the target pixel according to the noise influence degrees of other pixels in the preset window of the target pixel; correct an initial gray value of the target pixel according to a gray difference between the target pixel and the repairing pixel in the preset window, and a noise influence degree difference, to obtain a final gray value of the target pixel; and traverse all the to-be-de-noised pixels in each patient gastrointestinal image to obtain the final gray value of each to-be-de-noised pixel.

[0008] The image generation module is configured to obtain a de-noised patient gastrointestinal image according to the final gray value.

[0009] Further, the noise influence degree acquisition method comprises:

[0010] A Cartesian coordinate system is established with a lower left corner of each patient gastrointestinal image as an origin.

[0011] The noise influence degree is obtained according to a noise influence degree calculation formula, and the noise influence degree calculation formula is as follows:

[0012]

[0013] In the formula, (x, y) represents a position coordinate of the reference pixel; C(x, y) represents the noise influence degree of the reference pixel; M represents a pixel quantity of each patient gastrointestinal image; t m ′ represents a normalized gradient value of an mth pixel of each patient gastrointestinal image; N represents a pixel quantity in a preset neighborhood of the reference pixel; t n ′(x, y) represents a normalized gradient value of an nth pixel in the preset neighborhood of the reference pixel; f n (x, y) represents a gray value of the nth pixel in the preset neighborhood except the reference pixel; f(x, y) represents a gray value of the reference pixel; [] represents an integral function; and ln() represents a logarithmic function with a natural constant as a base number.

[0014] Further, the to-be-de-noised pixel acquisition method comprises:

[0015] Calculate the mean value of the noise influence degree of all pixel points in each patient's gastrointestinal image as a first mean value; the pixel points in each patient's gastrointestinal image with a noise influence degree greater than the first mean value are regarded as to-be-de-noised pixel points.

[0016] Further, the acquisition method of the repair pixel point comprises:

[0017] According to the noise influence degree of the target pixel point and other pixel points in the preset window, a repair evaluation parameter of the target pixel point is obtained, and the calculation formula is as follows:

[0018]

[0019] In the formula, i represents the serial number of the target pixel point; P i represents the repair evaluation parameter of the target pixel point; C i represents the noise influence degree of the target pixel point; represents the mean value of the noise influence degree of all pixel points in each patient's gastrointestinal image; C max represents the maximum value of the noise influence degree of the pixel points in each patient's gastrointestinal image;

[0020] A preset range is set, and the preset range is [0, 0.3), [0.3, 0.6), and [0.6, 1] respectively.

[0021] According to the preset range, the preset window is set to three different size windows, which are a first window, a second window, and a third window.

[0022] When the repair evaluation parameter of the target pixel point belongs to [0, 0.3), the three pixel points with the smallest noise influence degree in the first window are selected as the repair pixel points of the target pixel point.

[0023] When the repair evaluation parameter of the target pixel point belongs to [0.3, 0.6), the four pixel points with the smallest noise influence degree in the second window are selected as the repair pixel points of the target pixel point.

[0024] When the repair evaluation parameter of the target pixel point belongs to [0.6, 1], the five pixel points with the smallest noise influence degree in the third window are selected as the repair pixel points of the target pixel point.

[0025] Further, the acquisition method of the final gray value comprises:

[0026] The final gray value is obtained according to a final gray value calculation formula, and the final gray value calculation formula is as follows:

[0027]

[0028] In the formula, i represents the serial number of the target pixel point; f′ irepresents the final gray value of the target pixel point; f i represents the initial gray value of the target pixel point; Q represents the number of patching pixel points of the target pixel point; f i，q represents the gray value of the qth patching pixel point of the target pixel point; C i represents the noise influence degree of the target pixel point; C i，q represents the noise influence degree of the qth patching pixel point of the target pixel point; C q min represents the minimum value of the noise influence degree of all patching pixel points of the target pixel point.

[0029] A method for processing vital sign data of a patient in a digestive endoscopy examination, the method comprising:

[0030] Obtaining a stomach image and an intestinal tract image of the patient, and collectively referring to the stomach image and the intestinal tract image as patient gastrointestinal images;

[0031] Optionally selecting one pixel point in each patient gastrointestinal image as a reference pixel point; obtaining a noise influence degree of the reference pixel point according to a difference between a gradient distribution in a preset neighborhood of the reference pixel point and a gradient distribution in each patient gastrointestinal image, and a gray difference between the reference pixel point and other pixel points in the preset neighborhood; screening out to-be-de-noised pixel points in each patient gastrointestinal image according to the noise influence degrees of all pixel points in each patient gastrointestinal image; optionally selecting one to-be-de-noised pixel point as a target pixel point; screening out patching pixel points in a preset window of the target pixel point according to the noise influence degrees of other pixel points in the preset window of the target pixel point; and correcting an initial gray value of the target pixel point according to a gray difference between the target pixel point and the patching pixel points in the preset window, and a noise influence degree difference, to obtain a final gray value of the target pixel point;

[0032] Traversing all to-be-de-noised pixel points of each patient gastrointestinal image to obtain a final gray value of each to-be-de-noised pixel point.

[0033] A computer readable storage medium, the computer readable storage medium storing a computer program, the computer program being executed by a processor to implement the steps of the above-mentioned vital sign data processing system for a patient in a digestive endoscopy examination.

[0034] A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the above-mentioned vital sign data processing system for a patient in a digestive endoscopy examination when executing the computer program.

[0035] The present application has the following beneficial effects:

[0036] The present application firstly acquires the stomach image and the intestinal tract image of the patient, and since the same analysis is required for the stomach image and the intestinal tract image in the subsequent steps, in order to facilitate the description, the stomach image and the intestinal tract image are collectively referred to as the patient's gastrointestinal image; since the stomach and the intestinal tract of the human body have certain folds on the surface, the image features of each patient's gastrointestinal image are that there is rich edge information, and the gray scale features are relatively uniform, in the case of noise interference, local edge information distortion or local pixel gray scale value and the surrounding pixel gray scale value difference is too large may occur in each patient's gastrointestinal image, therefore, the influence of noise on each patient's gastrointestinal image is analyzed, the noise influence degree of the pixel is analyzed, and then the pixel to be denoised is screened out; since the pixel to be denoised needs to be denoised by pixel repair, but the denoising degree required by the pixel affected by different noises is also different, therefore, the noise influence degree of other pixels in the preset window of the pixel to be denoised is screened out to obtain the repair pixel in the preset window of the target pixel; the difference between the pixel to be denoised and the normal pixel is compensated by the gray scale value compensation method, and then the initial gray scale value of the target pixel is corrected according to the gray scale difference between the target pixel and the repair pixel in the preset window and the noise influence degree difference, to obtain the final gray scale value of the target pixel; and then the patient's gastrointestinal image after noise reduction is obtained. The present application can remove the noise influence in the patient's gastrointestinal image as much as possible, so as to obtain an image that can accurately identify the characteristics of the disease source. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, below, a brief introduction will be given to the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0038] Figure 1 A block diagram of a digestive endoscopy patient vital sign data processing system is provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined object, the specific implementation, structure, features and effects of a digestive endoscopy patient vital sign data processing system according to the present application are described in detail below in combination with the drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0040] Unless otherwise defined, 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 application belongs.

[0041] The specific scheme of the vital sign data processing system for patients undergoing digestive endoscopy provided by the present application is specifically described below in combination with the drawings.

[0042] Referring to Figure 1 which shows a vital sign data processing system for patients undergoing digestive endoscopy provided by an embodiment of the present application, the system comprises an image acquisition module 101, a pixel repair module 102 and an image generation module 103, and the specific steps include:

[0043] The image acquisition module 101 acquires the stomach image and the intestinal tract image of the patient, and the stomach image and the intestinal tract image are collectively referred to as the intestinal and stomach image of the patient.

[0044] The embodiment of the present application is mainly applied to the scene of denoising the intestinal tract image and the stomach image acquired by using digestive endoscopy, so the stomach image and the intestinal tract image of the patient are acquired first. Since the same analysis is required for the stomach image and the intestinal tract image in the subsequent steps, in order to facilitate description, the stomach image and the intestinal tract image are collectively referred to as the intestinal and stomach image of the patient.

[0045] In the embodiment of the present application, before the patient undergoes the related examination of digestive endoscopy, the related preparation work needs to be done, for example, fasting solid food for 6-8 hours before gastroscopy, and fasting water for 4 hours. 1-3 days before enteroscopy, eat porridge, noodles, egg soup, etc., avoid vegetables, fruits, foods with seeds, and take oral laxatives (such as compound polyethylene glycol electrolyte powder) 4-6 hours before examination until clear water is discharged. Complete electrocardiogram, blood routine, coagulation function, infectious disease screening. After completing a series of preparation work, the patient is subjected to related digestive endoscopy examination, and the stomach image and intestinal tract image of the patient can be obtained through digestive endoscopy. It should be noted that the image acquisition process is a technical means known to those skilled in the art, and is not limited or described here.

[0046] The pixel repairing module 102: optionally taking one pixel point in each patient gastrointestinal image as a reference pixel point; obtaining the noise influence degree of the reference pixel point according to the difference between the gradient distribution in the preset neighborhood of the reference pixel point and the gradient distribution in each patient gastrointestinal image, and the gray difference between the reference pixel point and other pixel points in the preset neighborhood; screening out the pixel points to be denoised in each patient gastrointestinal image according to the noise influence degree of all pixel points in each patient gastrointestinal image; optionally taking one pixel point to be denoised as a target pixel point; screening out the repairing pixel points in the preset window of the target pixel point according to the noise influence degree of other pixel points in the preset window of the target pixel point; correcting the initial gray value of the target pixel point according to the gray difference between the target pixel point and the repairing pixel points in the preset window, and the difference in noise influence degree, to obtain the final gray value of the target pixel point; traversing all pixel points to be denoised in each patient gastrointestinal image to obtain the final gray value of each pixel point to be denoised.

[0047] Since the stomach and intestinal surface of the human body have certain folds, the image features of each patient gastrointestinal image are that there is rich edge information, and the gray features are relatively uniform. In the case of noise interference, local edge information distortion or the difference between the local pixel point gray value and the surrounding pixel point gray value is too large in each patient gastrointestinal image, therefore, in order to analyze the influence of noise on each patient gastrointestinal image, in the embodiment of the present application, the noise influence degree of the reference pixel point is obtained according to the difference between the gradient distribution in the preset neighborhood of the reference pixel point and the gradient distribution in each patient gastrointestinal image, and the gray difference between the reference pixel point and other pixel points in the preset neighborhood.

[0048] Preferably, in one embodiment of the present application, the method for obtaining the noise influence degree comprises:

[0049] A Cartesian coordinate system is established with the lower left corner of each patient gastrointestinal image as the origin, and the gradient value of the pixel point corresponding to each coordinate position is normalized to obtain the normalized gradient value.

[0050] The noise influence degree is obtained according to the noise influence degree calculation formula, and the noise influence degree calculation formula is as follows:

[0051]

[0052] In the formula, (x, y) represents the position coordinates of the reference pixel point; C(x, y) represents the noise influence degree of the reference pixel point; M represents the number of pixel points of each patient gastrointestinal image; t m m represents the normalized gradient value of the mth pixel point of each patient gastrointestinal image; N represents the number of pixel points in the preset neighborhood of the reference pixel point; t nf(x,y) represents the normalized gradient value of the n-th pixel point in the preset neighborhood of the reference pixel point; f n (x,y) represents the gray value of the n-th pixel point in the preset neighborhood except the reference pixel point; f(x,y) represents the gray value of the reference pixel point; [] represents the rounding function; ln() represents the logarithmic function with the natural constant as the base number.

[0053] In the noise influence degree calculation formula, if the reference pixel point is in an edge-rich area, such as a wrinkle area, the gradient value in the preset neighborhood is high, at this time, even if the reference pixel point is a noise pixel point, the degree of noise influence on the reference pixel point is not obvious due to the characteristics of the edge-rich area; if the overall gradient value of the pixel points in the preset neighborhood is small, if there is a noise pixel point, the pixel point will be more prominent compared to other pixel points, and such a preset neighborhood is more susceptible to noise; at this time, the ratio between each patient gastrointestinal image and the average gradient of the pixel points in the preset neighborhood is calculated, if the ratio is less than 1, and the smaller the ratio is, it is considered that the edge information richness of the preset neighborhood is greater than the edge information richness of the overall image, which means that the preset neighborhood is a high gradient value area and is less affected by noise, and the noise influence degree of the reference pixel point is smaller, if the ratio is greater than 1, and the greater the ratio is, it is considered that the edge information richness of the preset neighborhood is less than the edge information richness of the overall image, at this time, the reference pixel point in the preset neighborhood is more susceptible to noise, which means that the noise influence degree of the reference pixel point is greater; if the average difference in gray value between the reference pixel point and other pixel points in the preset neighborhood is greater, it means that there is more likely to be a noise pixel point in the preset neighborhood, or the reference pixel point is a noise pixel point, at this time, it means that the reference pixel point is more affected by noise, and the noise influence degree of the reference pixel point is greater.

[0054] According to the noise influence degree of all pixel points in each patient gastrointestinal image, the pixel points to be denoised in each patient gastrointestinal image are screened out. Preferably, in an embodiment of the present application, the method for obtaining the pixel points to be denoised comprises:

[0055] The average value of the noise influence degree of all pixel points in each patient gastrointestinal image is calculated as a first average value; since the gradient feature and the gray feature difference between the noise pixel points and other normal pixel points in each patient gastrointestinal image are huge, the pixel points with the noise influence degree greater than the first average value in each patient gastrointestinal image are taken as the pixel points to be denoised.

[0056] In a subsequent step, the pixel points to be denoised need to be repaired and denoised, but the denoising degree required by the pixel points affected by different noises is not the same, so in the embodiment of the application, the pixel points in the preset window of the pixel points to be denoised are used for denoising. First, an optional pixel point to be denoised is selected as a target pixel point; according to the noise influence degree of other pixel points in the preset window of the target pixel point, a repair pixel point in the preset window of the target pixel point is selected.

[0057] Preferably, in an embodiment of the application, the method for obtaining the repair pixel point comprises:

[0058] According to the noise influence degree of the target pixel point and other pixel points in the preset window, a repair evaluation parameter of the target pixel point is obtained, and the calculation formula is as follows:

[0059]

[0060] In the formula, i represents the serial number of the target pixel point; P i represents the repair evaluation parameter of the target pixel point; C i represents the noise influence degree of the target pixel point; represents the average value of the noise influence degree of all pixel points in each patient gastrointestinal image; C max represents the maximum value of the noise influence degree of the pixel points in each patient gastrointestinal image.

[0061] In the repair evaluation parameter calculation formula, the difference between the noise influence degree of the target pixel point and the average value of the noise influence degree of all pixel points in each patient gastrointestinal image is greater, indicating that the denoising degree required by the target pixel point is greater, that is, the repair evaluation parameter of the target pixel point is higher; and then is normalized to unify the dimension.

[0062] A preset range is set, and the preset range is [0, 0.3), [0.3, 0.6), and [0.6, 1] respectively; the preset window is set to three different sizes of windows according to the preset range, which are a first window, a second window, and a third window; in an embodiment of the application, the first window is set to a 5x5 rectangular region with the target pixel point as the center, the second window is set to a 7x7 rectangular region with the target pixel point as the center, and the first window is set to a 9x9 rectangular region with the target pixel point as the center.

[0063] ​In one embodiment of the present application, when the repair evaluation parameter of the target pixel point belongs to [0, 0.3), the three pixel points with the least noise influence degree in the first window are selected as the repair pixel points of the target pixel point; when the repair evaluation parameter of the target pixel point belongs to [0.3, 0.6), the four pixel points with the least noise influence degree in the second window are selected as the repair pixel points of the target pixel point; and when the repair evaluation parameter of the target pixel point belongs to [0.6, 1], the five pixel points with the least noise influence degree in the third window are selected as the repair pixel points of the target pixel point.

[0064] In the embodiment of the present application, the difference between the to-be-denoised pixel point and the normal pixel point is compensated by the method of gray value compensation, so that the initial gray value of the target pixel point is corrected according to the gray difference and the noise influence degree difference between the target pixel point and the repair pixel points in the preset window, and the final gray value of the target pixel point is obtained.

[0065] Preferably, the method for obtaining the final gray value in one embodiment of the present application comprises:

[0066] The final gray value is obtained according to the final gray value calculation formula, and the final gray value calculation formula is as follows:

[0067]

[0068] In the formula, i represents the serial number of the target pixel point; f' i represents the final gray value of the target pixel point; f i represents the initial gray value of the target pixel point; Q represents the number of repair pixel points of the target pixel point; f i，q represents the gray value of the qth repair pixel point of the target pixel point; C i represents the noise influence degree of the target pixel point; C i，q represents the noise influence degree of the qth repair pixel point of the target pixel point; C q min represents the minimum value of the noise influence degree of all repair pixel points of the target pixel point.

[0069] In the final gray value calculation formula, the difference value C i -C i，q between the noise influence degree of the target pixel point and each repair pixel point reflects the repair degree of the repair pixel point to the target pixel point, wherein the greater the difference value, the greater the influence of the noise on the target pixel point, and the higher the repair degree of the repair pixel point to the target pixel point, that is, the higher the weight of the gray difference between the repair pixel point and the target pixel point, at this time, C i -C i，q is normalized and multiplied by [f i -f i，qMultiply the values ​​to obtain the compensation grayscale corresponding to each repaired pixel, use the average compensation grayscale of all repaired pixels as the correction value of the target pixel, and add them together to obtain the final grayscale value of the target pixel.

[0070] Iterate through all the pixels to be denoised in each patient's gastrointestinal image to obtain the final grayscale value of each pixel.

[0071] Image generation module 103: Obtains the denoised patient's gastrointestinal image based on the final grayscale value.

[0072] In one embodiment of the present invention, the gray values ​​of the pixels to be denoised in each original patient gastrointestinal image are replaced with the final gray values, and the gray values ​​of each pixel in the patient gastrointestinal image are finally obtained, thereby ending the denoising operation of each patient gastrointestinal image and obtaining the denoised patient gastrointestinal image.

[0073] In summary, the process involves acquiring images of the patient's stomach and intestines, collectively referred to as the patient's gastrointestinal images. A single pixel is selected from each image as a reference pixel. The noise level of the reference pixel is determined by the difference between its gradient distribution within a preset neighborhood and the gradient distribution in each image, as well as the grayscale difference between the reference pixel and other pixels within its preset neighborhood. Based on the noise levels of all pixels in each image, pixels to be denoised are selected. One pixel is then chosen as the target pixel. Based on the noise levels of other pixels within the target pixel's preset window, repair pixels are selected within that window. The initial grayscale value of the target pixel is corrected based on the grayscale difference between the target pixel and the repair pixels within the preset window, as well as the difference in noise levels, to obtain the final grayscale value. Finally, all pixels in each image are denoised to obtain their final grayscale value.

[0074] A second objective of one embodiment of the present invention is to provide a method for processing vital sign data of patients undergoing digestive endoscopy, the method comprising:

[0075] Obtain images of the patient's stomach and intestines, and refer to these images collectively as the patient's gastrointestinal images;

[0076] Optionally, one pixel in each patient gastrointestinal image is taken as a reference pixel; the noise influence degree of the reference pixel is obtained according to the difference between the gradient distribution in a preset neighborhood of the reference pixel and the gradient distribution in each patient gastrointestinal image, and the gray difference between the reference pixel and other pixels in the preset neighborhood; the to-be-denoised pixel in each patient gastrointestinal image is screened out according to the noise influence degree of all pixels in each patient gastrointestinal image; optionally, one to-be-denoised pixel is taken as a target pixel; the repair pixel in a preset window of the target pixel is screened out according to the noise influence degree of other pixels in the preset window of the target pixel; the initial gray value of the target pixel is corrected according to the gray difference between the target pixel and the repair pixel in the preset window, and the difference in noise influence degree, to obtain the final gray value of the target pixel.

[0077] All the to-be-denoised pixels in each patient gastrointestinal image are traversed to obtain the final gray value of each to-be-denoised pixel.

[0078] A third object of the embodiments of the present application is to provide a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the above-mentioned digestive endoscopy patient vital sign data processing system when executing the computer program.

[0079] A fourth object of the embodiments of the present application is to provide a computer readable storage medium, which stores a computer program, and the computer program implements the steps of the above-mentioned digestive endoscopy patient vital sign data processing system when executed by a processor.

[0080] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0081] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other, and each embodiment mainly describes the difference from other embodiments.

Claims

1. A vital sign data processing system for patients undergoing a digestive endoscopy, characterized in that, The system comprises: An image acquisition module, configured to acquire a stomach image and an intestinal tract image of a patient, and collectively refer to the stomach image and the intestinal tract image as patient gastrointestinal images; A pixel repairing module, configured to select an optional pixel point in each patient gastrointestinal image as a reference pixel point; obtain a noise influence degree of the reference pixel point according to a difference between a gradient distribution in a preset neighborhood of the reference pixel point and a gradient distribution in each patient gastrointestinal image, and a gray difference between the reference pixel point and other pixel points in the preset neighborhood; select a pixel point to be denoised in each patient gastrointestinal image according to the noise influence degrees of all pixel points in each patient gastrointestinal image; select an optional pixel point to be denoised as a target pixel point; select a repairing pixel point in a preset window of the target pixel point according to the noise influence degrees of other pixel points in the preset window; correct an initial gray value of the target pixel point according to a gray difference between the target pixel point and the repairing pixel point in the preset window, and a noise influence degree difference, and obtain a final gray value of the target pixel point; and traverse all pixel points to be denoised in each patient gastrointestinal image to obtain the final gray value of each pixel point to be denoised. An image generation module, configured to obtain a denoised patient gastrointestinal image according to the final gray value.

2. The system for processing vital sign data of a patient undergoing a digestive endoscopy according to claim 1, wherein, The method for obtaining the noise influence degree comprises: A Cartesian coordinate system is established with a lower left corner of each patient gastrointestinal image as an origin; The noise influence degree is obtained according to a noise influence degree calculation formula, as shown below: In the formula, (x, y) represents the position coordinates of the reference pixel point; C(x, y) represents the noise influence degree of the reference pixel point; M represents the number of pixel points of each patient gastrointestinal image; t m ′ represents the normalized gradient value of the mth pixel point of each patient gastrointestinal image; N represents the number of pixel points in the preset neighborhood of the reference pixel point; t n ′(x, y) represents the normalized gradient value of the nth pixel point in the preset neighborhood of the reference pixel point; f n (x, y) represents the gray value of the nth pixel point in the preset neighborhood except the reference pixel point; f(x, y) represents the gray value of the reference pixel point; [] represents the rounding function; ln() represents the logarithmic function with the natural constant as the base.

3. The system for processing vital sign data of a patient undergoing a digestive endoscopy according to claim 1, wherein, The method for obtaining the pixel point to be denoised comprises: A first mean value is calculated by taking a mean value of the noise influence degrees of all pixel points in each patient gastrointestinal image; and a pixel point in each patient gastrointestinal image with a noise influence degree greater than the first mean value is selected as a pixel point to be denoised.

4. The system for processing vital sign data of a patient undergoing a digestive endoscopy according to claim 1, wherein, The method for obtaining the repairing pixel point comprises: A repairing judgment parameter of the target pixel point is obtained according to the noise influence degrees of other pixel points in the preset window, and a calculation formula is as shown below: In the formula, i represents the serial number of the target pixel point; P i represents the repair evaluation parameter of the target pixel point; C i represents the noise influence degree of the target pixel point; represents the noise influence degree mean value of all pixel points in each patient gastrointestinal image; C max represents the maximum value of the noise influence degree of the pixel points in each patient gastrointestinal image; A preset range is set, and the preset range is [0, 0.3), [0.3, 0.6), and [0.6, 1] respectively; The preset window is set as three different size windows according to the preset range, and the three different size windows are a first window, a second window, and a third window respectively; When the repairing judgment parameter of the target pixel point belongs to [0, 0.3), three pixel points with the smallest noise influence degrees in the first window are selected as the repairing pixel points of the target pixel point; When the repairing judgment parameter of the target pixel point belongs to [0.3, 0.6), four pixel points with the smallest noise influence degrees in the second window are selected as the repairing pixel points of the target pixel point; When the repairing judgment parameter of the target pixel point belongs to [0.6, 1], five pixel points with the smallest noise influence degrees in the third window are selected as the repairing pixel points of the target pixel point.

5. The system for processing vital sign data of a patient undergoing a digestive endoscopy according to claim 1, wherein, The method for obtaining the final gray value comprises: The final gray value is obtained according to a final gray value calculation formula, as shown below: In the formula, i represents the serial number of the target pixel point; f i represents the final gray value of the target pixel point; f i represents the initial gray value of the target pixel point; Q represents the number of the patching pixel points of the target pixel point; f i，q represents the gray value of the qth patching pixel point of the target pixel point; C i represents the noise influence degree of the target pixel point; C i,q represents the noise influence degree of the qth patching pixel point of the target pixel point; C q min represents the minimum value of the noise influence degrees of all the patching pixel points of the target pixel point.

6. A method of processing vital sign data of a patient undergoing a digestive endoscopy, the method comprising: receiving vital sign data of the patient; determining a vital sign trend of the patient; and displaying the vital sign trend of the patient. The method comprises: Acquiring a stomach image and an intestinal tract image of a patient, and collectively referring to the stomach image and the intestinal tract image as patient gastrointestinal images; Optionally, one pixel in each patient gastrointestinal image is taken as a reference pixel; the noise influence degree of the reference pixel is obtained according to the difference between the gradient distribution in a preset neighborhood of the reference pixel and the gradient distribution in each patient gastrointestinal image, and the gray difference between the reference pixel and other pixels in the preset neighborhood; the to-be-denoised pixel in each patient gastrointestinal image is screened out according to the noise influence degree of all pixels in each patient gastrointestinal image; optionally, one to-be-denoised pixel is taken as a target pixel; the repair pixel in a preset window of the target pixel is screened out according to the noise influence degree of other pixels in the preset window of the target pixel; the initial gray value of the target pixel is corrected according to the gray difference between the target pixel and the repair pixel in the preset window, and the noise influence degree difference, to obtain the final gray value of the target pixel; All to-be-denoised pixels of each patient gastrointestinal image are traversed to obtain the final gray value of each to-be-denoised pixel.

7. A computer-readable storage medium storing a computer program, wherein the computer program comprises the following steps of: receiving a request for a resource from a client; determining whether the client is authorized to access the resource; and if the client is authorized to access the resource, providing the resource to the client. The computer program, when executed by the processor, implements the steps of the digestive endoscopy patient vital sign data processing system according to any one of claims 1 to 5.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the digestive endoscopy patient vital sign data processing system according to any one of claims 1 to 5.

Images