An X-ray image processing system for prognostic analysis of enteritis

Abstract

The present invention relates to the field of image processing technology, and more specifically, to an X-ray image processing system for enteritis prognosis analysis, comprising: obtaining a grayscale image based on multi-threshold segmentation; obtaining the grayscale fluctuation degree of the grayscale image based on the histogram of the grayscale image; determining the degree of pixel clustering through connected domain analysis; obtaining an initial lesion probability by combining the grayscale fluctuation degree and the pixel clustering degree of the grayscale image; obtaining the probability of intestinal gas presence based on the fitting results of each grayscale image; adjusting the initial lesion probability based on the intestinal gas probability to obtain the lesion probability; obtaining transformation parameters of the grayscale image based on the lesion probability; and performing a linear transformation on the X-ray image based on the transformation parameters to obtain an enhanced intestinal X-ray image and visualize it. The present invention enhances the contrast between the lesion area and the surrounding area and reduces the visual effect of shadows caused by gas, thereby facilitating prognostic analysis by doctors.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to an X-ray image processing system for enteritis prognosis analysis. Background Art

[0002] Radiation enteritis is a radiation-induced disease caused by digestive tract damage due to extensive or prolonged exposure to radiation, requiring comprehensive assessment and therapeutic intervention. With technological advancements, hospitals' prognostic analysis systems for radiation enteritis are becoming increasingly sophisticated. They not only assess the severity of a patient's condition but also provide data on the patient's treatment progress, enabling doctors to provide timely rehabilitation advice. Intestinal X-ray examinations are a key assessment criterion. Accurate capture and upload of X-ray images directly impact the accuracy of doctors' disease assessment and diagnosis. However, the intestinal state of patients with radiation enteritis may affect contrast agent absorption and leakage, thereby reducing the contrast and image contrast. This not only complicates diagnosis but also hinders analysis of treatment efficacy. Therefore, X-ray images captured by the radiation enteritis prognostic analysis system need to be enhanced to increase contrast and enhance visualization. However, enhancing intestinal X-ray images based on the entire image is difficult to avoid image distortion, resulting in poor enhancement results. Summary of the Invention

[0003] The present invention provides an X-ray image processing system for enteritis prognosis analysis to solve the existing problems.

[0004] The X-ray image processing system for enteritis prognosis analysis of the present invention adopts the following technical solutions:

[0005] One embodiment of the present invention provides an X-ray image processing system for enteritis prognosis analysis, the system comprising the following modules:

[0006] The image preprocessing module is used to collect intestinal X-ray images of patients with radiation enteritis and perform grayscale processing; the obtained grayscale image is divided into multiple grayscale images using multi-threshold segmentation;

[0007] A lesion probability determination module is used to determine the grayscale fluctuation degree of multiple grayscale images based on the frequency fluctuation in the grayscale histogram of the grayscale image; quantify the degree of pixel clustering of the grayscale image based on the number, size and overlap of connected domains of the multiple grayscale images; and obtain the initial lesion probability of the grayscale image based on the grayscale fluctuation degree and pixel clustering degree of the grayscale image;

[0008] a lesion probability adjustment module for performing ellipse fitting based on the shape characteristics of the shadow area formed by intestinal gas and obtaining the probability of intestinal gas existing in the grayscale image based on the fitting results of each grayscale image; adjusting the initial lesion probability of the grayscale image based on the intestinal gas probability, and obtaining the adjusted image lesion probability as the final lesion probability;

[0009] An image enhancement module is used to obtain transformation parameters for performing linear transformation enhancement on each grayscale image according to the lesion probability and to enhance the X-ray image according to the obtained parameters;

[0010] The lesion segmentation and recognition module is used to segment the enhanced image.

[0011] Preferably, the specific method for obtaining the grayscale image is as follows:

[0012] The grayscale image is segmented using the multi-threshold segmentation algorithm. thresholds, and the jth threshold is recorded as and , according to the obtained The threshold divides the gray value into multiple levels, which are ,in Indicates the Threshold value, gray value is The gray levels of all pixels in the interval are divided into Level grayscale, the obtained The pixel value of the gray level is marked as 1, and the other pixel values ​​are marked as 0. The binary image is used as the mask image, and then the mask image is multiplied with the gray image to obtain the first Grayscale image, get A grayscale image.

[0013] Preferably, the method of determining the grayscale fluctuation degree of the entire grayscale images according to the fluctuation of the frequency in the grayscale histogram of the grayscale images includes the following specific methods:

[0014] Obtain the grayscale histogram of each grayscale image, and quantify the grayscale fluctuation degree of each grayscale and image according to the grayscale value frequency variance in the grayscale image histogram. The specific formula is as follows:

[0015]

[0016]

[0017] in, Indicates the Segmentation threshold; Indicates the The grayscale fluctuation degree of a grayscale image; Indicates the The interval corresponding to the grayscale image The grayscale values, and , Representation interval The number of grayscale values ​​contained in ; Indicates the The average grayscale value in the grayscale image; Indicates in The histogram of the grayscale image Grayscale value The frequency of occurrence.

[0018] Preferably, the method of quantifying the degree of pixel clustering of the grayscale image based on the number, size and overlap of connected domains of the plurality of grayscale images as indicators; and obtaining the initial lesion probability of the grayscale image in combination with the grayscale fluctuation degree and pixel clustering degree of the grayscale image includes the following specific formula:

[0019]

[0020] in, Indicates the The probability that there is a lesion area in a grayscale image; Indicates the The degree of pixel grayscale fluctuation in a grayscale image; Indicates the The number of connected components in a grayscale image; Indicates the The average area of ​​the connected domain formed in the grayscale image; Indicates the The average value of the sum of the center distances between two connected domains in a grayscale image; Indicates the degree of pixel clustering quantified by the size, number, and overlap of connected domains in each grayscale image; Represents an exponential function with a natural constant as its base.

[0021] Preferably, the probability of intestinal gas existing in the grayscale image is obtained according to the fitting result of each grayscale image, and the specific formula included is:

[0022]

[0023] in, Indicates the The average ellipse fitting effect of grayscale images, Indicates the The first grayscale image The best fitting result of the connected domain, represents the number of connected components in the grayscale image and , Indicates the The number of connected components in a grayscale image.

[0024] Preferably, the initial lesion probability of the grayscale image is adjusted according to the intestinal gas probability, and the adjusted image lesion probability is obtained as the final lesion probability, including the specific formula:

[0025]

[0026] in, represents the first The lesion probability of a grayscale image, Indicates the use of The probability of intestinal gas existence after normalization, Indicates the initial The lesion probability of a grayscale image.

[0027] Preferably, the method of obtaining the transformation parameters for performing linear transformation enhancement on each grayscale image according to the lesion probability includes the following specific methods:

[0028] The greater the probability of lesions in the grayscale image, the greater the degree of enhancement, and vice versa. To enhance the contrast, the grayscale value of the area with a high probability of lesions needs to be reduced, and the grayscale value of the area with a low probability of lesions needs to be increased. The specific calculation formula is as follows:

[0029]

[0030] in, Indicates the The transformation coefficient when the gray level function is linearly transformed and enhanced, is a hyperparameter; represents the tangent function; represents the hyperbolic tangent function.

[0031] Preferably, the method of acquiring the transformation parameters for performing linear transformation enhancement on each grayscale image according to the lesion probability and enhancing the X-ray image according to the acquired parameters includes the following specific methods:

[0032] The linear transformation enhancement formula is constructed according to the transformation parameters of each grayscale image as follows:

[0033]

[0034] in, express The pixel values ​​of the output image of a grayscale image, Indicates the In the grayscale image The gray value of a pixel, is a hyperparameter, take , For the The average gray value of a grayscale image.

[0035] The beneficial effects of the technical solution of the present invention are as follows: by performing grayscale segmentation on the intestinal X-ray images of patients with enteritis, the image corresponding to each grayscale is obtained, and the grayscale fluctuation degree of the entire grayscale image is determined according to the grayscale frequency fluctuation of the grayscale image histogram, and then by analyzing the number, size and overlap of connected domains in the grayscale image, the distribution and aggregation degree of pixel points in the grayscale image is determined, and the probability of the existence of lesions in each grayscale image is preliminarily determined; considering the influence of intestinal gas, the probability of the existence of intestinal gas in each grayscale image is obtained by shape fitting the morphological characteristics of the gas shadow, and the final lesion probability is obtained by adjusting the preliminarily determined disease probability through the gas probability; finally, the transformation parameters are determined according to the lesion probability and the grayscale of the image is enhanced, thereby improving the intestinal The adaptive enhancement of the line image enhances the contrast between the lesion area and the surrounding area and reduces the visual effect of the shadow caused by the gas. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. 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 any creative work.

[0037] Figure 1 The present invention is a flowchart of the steps of an X-ray image processing system for enteritis prognosis analysis. DETAILED DESCRIPTION

[0038] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effectiveness of an X-ray image processing system for enteritis prognosis analysis according to the present invention. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0039] 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.

[0040] The following describes in detail a specific solution of an X-ray image processing system for enteritis prognosis analysis provided by the present invention with reference to the accompanying drawings.

[0041] See also Figure 1 , which shows a structural block diagram of an X-ray image processing system for enteritis prognosis analysis provided by one embodiment of the present invention, the method comprising the following steps:

[0042] The image preprocessing module 101 collects an intestinal X-ray image of an enteritis patient and performs grayscale processing to divide the image into multiple grayscale images.

[0043] Follow the doctor's instructions to correctly position the patient, obtain intestinal X-ray images and perform pretreatment.

[0044] It should be noted that, in order to achieve regional enhancement of X-ray images, the embodiment of the present invention first uses a multi-threshold segmentation algorithm to divide the grayscale value of the image. Multi-threshold segmentation is an existing technology and will not be elaborated here. The calculated threshold is used as the basis for dividing the grayscale interval. The present invention takes the empirical value J=9, and the j-th threshold is recorded as and , according to the obtained The thresholds divide the grayscale value into multiple levels: , , ,…, ), ,in Indicates the Threshold value, gray value is The gray levels of all pixels in the interval are divided into grayscale level, thus obtaining gray levels.

[0045] It should be noted that, since the complexity of the image corresponding to each gray level is different, the degree of enhancement is also different. Therefore, it is necessary to obtain each gray level image to facilitate the analysis of the complexity of its pixel distribution: First, mark the image at the first gray level. The pixel value of the first gray level is 1, and the other pixel values ​​are 0. The binary image is used as the mask image, and then the mask image is multiplied with the gray image of the intestinal X-ray image to obtain the first gray level. grayscale image, thereby obtaining A grayscale image.

[0046] At this point, all gray levels of the image are obtained through multi-threshold segmentation and multiple grayscale images are obtained according to the gray levels.

[0047] The lesion probability determination module 102 obtains the initial lesion probability of the grayscale image by combining the grayscale fluctuation degree and the pixel overlap degree of the grayscale image.

[0048] It should be noted that since the grayscale distribution of normal intestinal X-ray images is relatively uniform, while the grayscale values ​​of the diseased areas in the X-ray images of patients with radiation enteritis are larger or smaller than those of normal areas, the frequency fluctuation of the grayscale image histogram can reflect the complexity of the grayscale distribution of the image in that grayscale interval. Therefore, the embodiment of the present invention calculates the grayscale distribution fluctuation corresponding to each grayscale image according to the following formula, taking the j-th grayscale image as an example:

[0049] Get the grayscale mean of the j-th grayscale image, recorded as , get the gray value of any pixel i in the j-th gray image, denoted as , get the frequency of occurrence of the gray value of any pixel i in the j-th gray image, and record it as , the number of grayscale values ​​in the j-th grayscale image is recorded as , the grayscale fluctuation degree of the j-th grayscale image can be calculated according to the following mathematical formula:

[0050]

[0051] It should be noted that for the j-th level grayscale image, if the difference between different pixels and the grayscale mean is larger, the grayscale value distribution fluctuation is larger, and the calculated grayscale fluctuation degree is also larger. At the same time, in order to facilitate subsequent calculations, this embodiment performs linear normalization on the grayscale fluctuation degree result, so that .

[0052] Then use the above calculation formula to The grayscale images are calculated to obtain the overall grayscale fluctuation degree of each grayscale image, which provides a basis for the subsequent further analysis of the local pixel distribution of the grayscale image.

[0053] At this point, the overall grayscale fluctuation degree of each grayscale image is obtained by calculating the fluctuation of the histogram frequency of each grayscale image.

[0054] Then, by performing connected domain analysis on the grayscale image, the degree of clustering of pixel distribution in each grayscale image is quantified according to the number, size and overlap of connected domains, and the initial lesion probability of the grayscale image is determined.

[0055] It should be noted that in abdominal intestinal X-rays, patients with enteritis experience the generation of free gas within the abdominal cavity due to the rupture of gas-containing intestinal loops. This free gas appears as a low-density, clustered shadow area in the X-ray image. Therefore, combining the grayscale fluctuations of the acquired grayscale image, the stability of the lesion in each grayscale image is analyzed. By analyzing the clustering of local pixels in the grayscale image, the probability of the presence of a local lesion in the grayscale image is determined.

[0056] It should be noted that the pixels in the lesion area in the intestinal X-ray image are relatively dense, so we can first use the connected domain analysis to obtain the connected areas in each grayscale image, and then quantify the degree of aggregation of local pixels in the grayscale image by analyzing the number of connected domains contained in the grayscale image, the corresponding size of the connected domains, and the overlap of the connected domains.

[0057] It should be noted that when judging the degree of local pixel clustering in a grayscale image based on the distribution of connected domains in the grayscale image, if the degree of pixel clustering is high, it means that there may be a large number of connected domains with smaller areas in the grayscale image. Moreover, since there are a large number of connected domains, the overlapping areas caused are also large. Therefore, the embodiment of the present invention uses the number and area of ​​connected domains and the overlap between connected domains as indicators to adjust the influence of the overall grayscale fluctuation degree on the initial lesion probability judgment, so as to enhance the stability of the lesion probability judgment. The calculation form is as follows:

[0058]

[0059] in, Indicates the The probability that there is a lesion area in a grayscale image; Indicates the The degree of pixel grayscale fluctuation in a grayscale image; Indicates the The number of connected components in a grayscale image; Indicates the The average area of ​​the connected domain formed in the grayscale image; Indicates the The average value of the sum of the center distances between two connected domains in a grayscale image. If the center distance is smaller, it means that the connected domains are close to each other, otherwise the connected domains are more dispersed. It is used to quantify the overlap between connected domains. It means that the ratio of the area and number of connected domains is used to make the .

[0060] It should be noted that the embodiment of the present invention is Adjust the rate of change of the disease probability, if The larger the connected domain is, the larger the area and the smaller the distribution. The more discrete the pixel points in the grayscale image are, the more The center distance between adjacent connected components in the grayscale image As increases, the rate of decrease of pixel clustering becomes faster. Then, for these grayscale images, the probability of the presence of lesion areas may be low due to the influence of their surface features. On the contrary, when When it is small, it means that there are a large number of small connected domains in the image, and the pixel points in the image are relatively concentrated. Therefore, as the center distance between adjacent connected domains in the image increases, The longer the pixel clustering is, the slower it decreases, and the higher the probability that the grayscale image itself has lesions. Therefore, the embodiment of the present invention improves the accuracy of judging whether an image has lesions by the pixel clustering degree of the grayscale image.

[0061] At this point, the initial lesion probability of each grayscale image is obtained.

[0062] The lesion probability adjustment module 103 adjusts the initial lesion probability of the image according to the probability of intestinal gas in each grayscale image.

[0063] It should be noted that when enhancing intestinal X-ray images of patients with radiation enteritis, it is necessary to consider the impact of the gas present in the intestine itself on the determination of the lesion area, because the tiny area formed by the gas may be considered as the lesion area. Therefore, in order to weaken the impact of the gas area on the lesion area, the embodiment of the present invention uses the least squares method to fit an ellipse to each connected domain in the grayscale image based on the characteristics of the shadow of an approximate circle or ellipse usually formed by intestinal gas accumulation, and then adjusts the lesion probability calculated in the above steps based on the fitting effect as the probability of the presence of intestinal gas, so as to improve the accuracy of judging the lesion area.

[0064] First, the least squares method is used to fit an ellipse to the connected domain of the grayscale image. Assume that the equation of the fitted ellipse is expressed as:

[0065]

[0066] in is the horizontal and vertical coordinates of the ellipse equation, are the parameters of the ellipse equation.

[0067] Record In the grayscale image The first connected domain The horizontal and vertical coordinates of the pixel point are , according to the least squares principle, The first grayscale image Connected domain fitting results The objective function is:

[0068]

[0069] Then when The fitting effect is best when it reaches the minimum, so The partial derivatives of are 0, that is, when When , the corresponding ellipse is the best fitting ellipse, and the relevant parameters of the ellipse can be obtained. The minimum value is recorded as , recorded as The first grayscale image The best ellipse fitting effect of a connected domain.

[0070] It should be noted that due to The smaller the value of , the better the ellipse fitting effect is. In this case, the probability that the corresponding connected domain is the intestinal gas shadow area is greater. Because intestinal gas usually appears in gray or black shadows, it is more likely to be classified into the same grayscale image. Therefore, the embodiment of the present invention obtains the intestinal gas existence probability of each grayscale image by calculating the average value of the best fitting results:

[0071]

[0072] in, Indicates the The average ellipse fitting effect of grayscale images, Indicates the The first grayscale image The best fitting result of the connected domain, represents the number of connected components in the grayscale image and , Indicates the The number of connected components in a grayscale image.

[0073] It should be noted that if The smaller the value of , the better the ellipse fitting effect. At this time, the probability of gas shadows existing in the corresponding grayscale image is greater. If the calculated initial lesion probability is large, the probability of mistakenly identifying gas areas as lesion areas is greater due to the high probability of gas presence. Therefore, the lesion probability of the grayscale image needs to be reduced. Therefore, it is necessary to adjust the initial lesion probability based on the probability of intestinal gas presence. In this embodiment, the lesion probability of each grayscale image is adjusted as follows:

[0074]

[0075] in, represents the first The lesion probability of a grayscale image, Indicates the use of The probability of intestinal gas existence after normalization, Indicates the initial The lesion probability of a grayscale image.

[0076] It should be noted that the use of Multiplying the initial lesion probability to adjust the lesion probability, it is clear that due to the influence of intestinal gas, the probability of lesions in each grayscale image is reduced accordingly. A smaller value indicates a better fit of the connected domain of the grayscale image, a greater probability of intestinal gas, and a correspondingly larger adjustment to the initial lesion probability. This multiplication process results in a greater reduction in the initial lesion probability. This adjustment formula effectively reduces the impact of intestinal gas shadows on the lesion area, preventing over-enhancement of the gas shadow area.

[0077] At this point, the lesion probability of each grayscale image adjusted according to the gas presence probability is obtained.

[0078] The image enhancement module 104 determines the transformation parameters for linear transformation enhancement of the grayscale image according to the lesion probability, and performs linear transformation enhancement on the image.

[0079] It should be noted that the greater the probability of lesions in the grayscale image, the greater the degree of enhancement required. To make the lesion area more obvious, the pixel values ​​in the area with a high probability of lesions are increased through linear transformation. However, for areas with a low probability of lesions, the probability of shadows formed by intestinal gas is high, so the grayscale values ​​of images with sufficiently low lesion probabilities need to be reduced through linear transformation to enhance the visual effect of the gas shadow area and prevent it from affecting the judgment of the lesion area. Therefore, the embodiment of the present invention constructs the following relationship to determine the transformation parameters:

[0080]

[0081] in, Indicates the The transformation coefficient when the gray level function is linearly transformed and enhanced, is a hyperparameter, which indicates the limit on the size of the transformation coefficient. Usually, the value range of adjusting the image contrast is , so the embodiment of the present invention is based on This embodiment is not specifically limited. It can be determined according to the specific implementation situation; the relationship between the transformation coefficient and the lesion probability is used to construct the relationship between the two. Function relationship, and using the hyperbolic tangent function Perform normalization processing.

[0082] Finally, the intestinal X-ray image is enhanced according to the linear transformation algorithm based on the transformation parameters of each grayscale image. The transformation formula is as follows:

[0083]

[0084] in, express The pixel values ​​of the output image of a grayscale image, Indicates the In the grayscale image The gray value of a pixel, is a hyperparameter. In this embodiment, , For the The average gray value of a grayscale image.

[0085] It should be noted that the grayscale is divided into different degrees of linear transformation enhancement of intestinal X-ray images, which enhances the adaptability of the linear transformation algorithm in enhancing intestinal X-ray images, prevents over-enhancement or under-enhancement of the image, and can provide doctors with clearer intestinal X-ray images to guide their judgment of the patient's condition and recovery.

[0086] At this point, the intestinal X-ray images enhanced by the improved linear transformation enhancement algorithm were obtained.

[0087] The lesion segmentation and identification module 105 performs lesion segmentation and identification based on the enhanced intestinal X-ray image to assist doctors in prognosis analysis.

[0088] It should be noted that after adaptive linear transformation enhancement of X-ray images, the contrast between the lesion area and the normal area is enhanced, which can now more completely and accurately segment the intestinal lesion area, thereby obtaining a more precise lesion area, providing a basis for doctors to conduct prognostic analysis. At the same time, the X-ray images should be saved to the system so that doctors can promptly review and compare the patient's recovery status and analyze the condition.

[0089] Specifically, this embodiment uses a human interaction method to segment the X-ray image after adaptive linear transformation enhancement to ensure the accuracy of obtaining the lesion area.

[0090] Through the above steps, the X-ray image enhancement processing before the prognosis analysis of enteritis is completed.

[0091] The embodiment of the present invention performs grayscale segmentation on intestinal X-ray images of patients with enteritis to obtain images corresponding to each grayscale, determines the overall grayscale fluctuation degree of each grayscale image according to the grayscale frequency fluctuation of the grayscale image histogram, and then determines the distribution and aggregation degree of pixel points in the grayscale image by analyzing the number, size and overlap of connected domains in the grayscale image, and preliminarily determines the probability of the existence of lesions in each grayscale image; considering the influence of intestinal gas, the probability of the existence of intestinal gas in each grayscale image is obtained by shape fitting the morphological characteristics of the gas shadow, and adjusts the preliminarily determined disease probability by the gas probability to obtain the final lesion probability; finally, determines the transformation parameters according to the lesion probability and enhances the grayscale of the image, thereby improving the intestinal The adaptive enhancement of X-ray images enhances the contrast between the lesion area and the surrounding area and reduces the visual effect of the shadow caused by the gas. Doctors can perform prognostic analysis based on the X-ray images of patients with enteritis with stronger contrast.

[0092] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An X-ray image processing system for enteritis prognosis analysis, characterized in that: The system includes the following modules: An image preprocessing module is used to collect intestinal X-ray images of patients with radiation enteritis and perform grayscale processing to obtain grayscale images of intestinal X-ray images; and divide them into multiple grayscale images using multi-threshold segmentation; a lesion probability determination module, configured to determine the grayscale fluctuation degree of the plurality of grayscale images based on the fluctuation of the frequency in the grayscale histogram of the grayscale image; The degree of pixel clustering of the grayscale image is quantified based on the number, size, and overlap of connected domains of multiple grayscale images; the initial lesion probability of the grayscale image is obtained by combining the grayscale fluctuation degree and the pixel clustering degree of the grayscale image; a lesion probability adjustment module for performing ellipse fitting based on the shape characteristics of the shadow area formed by intestinal gas and obtaining the probability of intestinal gas existing in the grayscale image based on the fitting results of each grayscale image; adjusting the initial lesion probability of the grayscale image based on the intestinal gas probability, and obtaining the adjusted image lesion probability as the final lesion probability; An image enhancement module is used to obtain transformation parameters for performing linear transformation enhancement on each grayscale image according to the lesion probability and to enhance the X-ray image according to the obtained parameters; Lesion segmentation and recognition module, used to segment the enhanced image; The method of quantifying the degree of pixel clustering of the grayscale image based on the number, size, and overlap of connected domains of the plurality of grayscale images and obtaining the initial lesion probability of the grayscale image by combining the grayscale fluctuation degree and the pixel clustering degree of the grayscale image includes the following specific obtaining methods: The ratio of the average area of ​​the connected domain of each grayscale image to the number of connected domains in each grayscale image is recorded as the first ratio. The average value of the distance between any two connected domains in each grayscale image is obtained and recorded as the first mean. The product of the first mean and the first ratio is used to calculate the value of the negative exponential function with the natural constant e as the base, and recorded as the first function value. The product of the grayscale fluctuation degree of each grayscale image and the first function value is recorded as the initial lesion probability.

2. The X-ray image processing system for enteritis prognosis analysis according to claim 1, characterized in that: The method of dividing the image into multiple grayscale images by multi-threshold segmentation includes: A multi-threshold segmentation algorithm is used to obtain a mask image from the grayscale image of the intestinal X-ray image, and the mask image is multiplied with the grayscale image of the intestinal X-ray image to obtain multiple grayscale images.

3. The X-ray image processing system for enteritis prognosis analysis according to claim 2, characterized in that: The multi-threshold segmentation algorithm specifically includes: Setting the number of thresholds of the multi-threshold segmentation algorithm to J, where J is a first preset value; The jth threshold is recorded as and , divide the grayscale value into multiple levels: , , ,…, ), ,in Indicates the Threshold value, gray value is The gray levels of all pixels in the interval are divided into Grayscale level; The obtained The pixel value of the gray level is marked as 1, and the other pixel values ​​are marked as 0.

4. The X-ray image processing system for enteritis prognosis analysis according to claim 1, characterized in that: The method for determining the grayscale fluctuation degree of the plurality of grayscale images according to the fluctuation of the frequency in the grayscale histogram of the grayscale image includes the following specific acquisition methods: Obtain the grayscale mean in each grayscale image, record the difference between the grayscale value of the pixel point in each grayscale image and the grayscale mean as the first difference, obtain the frequency of each grayscale value in each grayscale image and record it as the first frequency, record the product of the square of the first difference and the first frequency as the first product, and record the cumulative sum of the first products as the grayscale fluctuation degree.

5. The X-ray image processing system for enteritis prognosis analysis according to claim 1, characterized in that: The specific formula for obtaining the probability of intestinal gas existing in the grayscale image according to the fitting result of each grayscale image is as follows: in, Indicates the The average ellipse fitting effect of grayscale images, Indicates the The first grayscale image The best fitting result of the connected domain, represents the number of connected components in the grayscale image and , Indicates the The number of connected components in a grayscale image.

6. The X-ray image processing system for enteritis prognosis analysis according to claim 1, characterized in that: The method of adjusting the initial lesion probability of the grayscale image according to the intestinal gas probability and obtaining the adjusted image lesion probability as the final lesion probability includes the following specific methods: in, represents the first The lesion probability of a grayscale image, Indicates the use of The probability of intestinal gas existence after normalization, Indicates the initial The lesion probability of a grayscale image.

7. The X-ray image processing system for enteritis prognosis analysis according to claim 1, characterized in that: The transformation parameters for performing linear transformation enhancement on each grayscale image are obtained according to the lesion probability, and the specific formula included is: in, Indicates the The transformation coefficient when the gray level function is linearly transformed and enhanced, is a hyperparameter; represents the tangent function; represents the hyperbolic tangent function.

8. The X-ray image processing system for enteritis prognosis analysis according to claim 1, characterized in that: The method of obtaining the transformation parameters for performing linear transformation enhancement on each grayscale image according to the lesion probability and enhancing the X-ray image according to the obtained parameters includes the following specific methods: The linear transformation enhancement formula is constructed according to the transformation parameters of each grayscale image as follows: in, express The pixel values ​​of the output image of a grayscale image, Indicates the In the grayscale image The gray value of a pixel, is a hyperparameter, take , For the The average grayscale value of a grayscale image.

Images