A method and system for enhancing liver CT images

Abstract

The present invention relates to the technical field of image enhancement, and particularly relates to a method and system for enhancing liver CT images. The invention obtains the initial window of each connected region; according to the density distribution of the pixel points in each initial window on the CT image, obtains the density change degree of each initial window; obtains the multi-scale images corresponding to the CT image, and according to the frequency domain distribution characteristics of the initial windows corresponding to the same position between different scale images, obtains the high-frequency information change degree of each initial window; further obtains the window correction coefficient of each initial window, corrects each initial window, and obtains the corrected window of each initial window; performs adaptive histogram equalization on different scale images according to the corrected window, and combines with the degree of chaos of the corresponding scale image for weighted fusion to obtain the enhanced CT image. The invention improves the effect of image enhancement by obtaining the accurate window size during image equalization processing.

Description

Technical Field

[0001] The present invention relates to the technical field of image enhancement, and particularly relates to a method and system for enhancing liver CT images. Background Art

[0002] Segmenting and extracting the liver region in abdominal CT images can be used in various fields such as medical teaching and clinical auxiliary treatment. However, the liver has characteristics such as low contrast with adjacent organs, weak boundaries, and large morphological differences among cases. Therefore, image enhancement of the liver in abdominal CT images still faces great difficulties.

[0003] Considering that the liver usually shows a relatively uniform gray-scale distribution in CT images, in the prior art, adaptive histogram equalization is adopted. That is, based on the window size obtained by experience, the image is segmented into several small regions, the histogram of each small region is calculated separately and equalized, and the local contrast of the image is enhanced. However, due to the size, shape, and different pathological characteristics of the liver, there are different information detail features. Using an inappropriate window size may lead to over-enhancement or under-enhancement of the image, resulting in a poor enhancement effect. Summary of the Invention

[0004] In order to solve the technical problem that an inappropriate window size may lead to over-enhancement or under-enhancement of the image, resulting in a poor enhancement effect, the purpose of the present invention is to provide a method and system for enhancing liver CT images, and the specific technical solutions adopted are as follows:

[0005] The present invention proposes a method for enhancing liver CT images, and the method includes:

[0006] Obtain the CT image of the liver;

[0007] Obtain the connected domains of the CT image according to the gray-scale distribution of the pixel points on the CT image; obtain the initial window of each connected domain according to the morphological characteristics of each connected domain; obtain the density change degree of each initial window according to the density distribution of the pixel points in each initial window on the CT image;

[0008] Obtain the multi-scale images corresponding to the CT image; obtain the high-frequency information change degree of each initial window according to the frequency-domain distribution characteristics of the initial windows at the same position corresponding to different-scale images; obtain the window correction coefficient of each initial window according to the density change degree and high-frequency information change degree of each initial window; correct each initial window according to the window correction coefficient to obtain the corrected window of each initial window;

[0009] Perform adaptive histogram equalization on different-scale images according to the corrected window, and perform weighted fusion in combination with the chaos degree of the corresponding-scale images to obtain the enhanced CT image.

[0010] Further, the method for obtaining the connected domain includes:

[0011] Perform CANNY edge detection on the CT image to obtain the edge curve in the CT image, and use the independent region enclosed by all closed edge curves as the connected domain.

[0012] Further, the method for obtaining the initial window includes:

[0013] Obtain the square of the number of edge pixels in each connected domain as the square of the edge pixels; obtain the ratio of the number of all pixels in each connected domain to the square of the edge pixels as the first morphological coefficient; obtain the product of the preset ratio parameter and the first morphological coefficient as the shape factor.

[0014] If the shape factor of the connected domain is greater than the preset factor threshold, set the initial window of the corresponding connected domain as the preset first window; otherwise, set the initial window of the corresponding connected domain as the preset second window, where the preset second window is larger than the preset first window. The initial window is a square region with equal width centered on the centroid of the connected domain.

[0015] Further, the method for obtaining the degree of density change includes:

[0016] Obtain the HU value of each pixel point on the CT image;

[0017] Obtain the mean value of the difference between the HU values of different pixel points and the preset liver HU value as the degree of density change of each initial window.

[0018] Further, the method for obtaining the degree of high-frequency information change includes:

[0019] For any scale image, obtain the frequency-domain image of each initial window;

[0020] Obtain the sum of the amplitudes of all high-frequency information in each frequency-domain image as the first amplitude; obtain the sum of all frequency-domain amplitudes in each frequency-domain image as the second amplitude; obtain the ratio of the first amplitude to the second amplitude as the high-frequency ratio.

[0021] According to the difference in the high-frequency ratio corresponding to the initial window at the same position between different adjacent scale images, obtain the degree of high-frequency information change of each initial window, where the difference in the high-frequency ratio is positively correlated with the degree of high-frequency information change.

[0022] Further, the method for obtaining the high-frequency information includes:

[0023] For any frequency-domain image, obtain the relative distance between the pixel points with non-zero gray values and the center point of the frequency-domain image, construct a distance histogram of the relative distances corresponding to all pixel points with non-zero gray values, and use Otsu's method to segment the distance histogram to obtain the segmentation region of the distance histogram.

[0024] Select the one with the largest average relative distance in the segmentation region, and use the corresponding pixel points as the high-frequency information in the spectral image.

[0025] Further, the method for obtaining the window correction coefficient includes:

[0026] Fuse the density change degree and the high-frequency information change degree of each initial window to obtain the window correction coefficient corresponding to the initial window.

[0027] Further, the method for obtaining the corrected window includes:

[0028] Obtain the difference between the positive integer 1 and the window correction coefficient as the adjustment weight.

[0029] Obtain the product of the adjustment weight and the initial size of the initial window, calculate the sum of the product result and the initial size as the corrected size, and obtain the corrected window.

[0030] Further, the method for obtaining the multi-scale image includes:

[0031] Use a Gaussian pyramid to obtain the multi-scale image corresponding to the CT image.

[0032] The present invention also proposes a liver CT image enhancement system, including 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 any one of the above-mentioned liver CT image enhancement methods are implemented.

[0033] The present invention has the following beneficial effects:

[0034] The present invention obtains the connected components of a CT image based on the gray-scale distribution of pixel points on the CT image, which helps to divide the image into regions with similar gray-scale values and enables more targeted local analysis. Since the shape and size of the liver are important factors for determining the analysis window, an initial window for each connected component is obtained according to the morphological characteristics of each connected component. According to the density distribution of pixel points within each initial window on the CT image, the degree of density change of each initial window is obtained, which reflects the complexity of the tissue within the initial window. A multi-scale image corresponding to the CT image is obtained, which reflects the complexity or lesion degree of the tissue within the window. According to the frequency-domain distribution characteristics of the initial windows at the same positions corresponding to different-scale images, the degree of change in high-frequency information of each initial window is obtained, which reflects the edge and texture characteristics of the image within the window and helps to evaluate the complexity and richness of details of the image within the window. Furthermore, a window correction coefficient for each initial window is obtained, and each initial window is corrected to obtain a corrected window for each initial window, which can more accurately adapt to the characteristics of different tissue regions and optimize the performance of histogram equalization. Adaptive histogram equalization is performed on different-scale images according to the corrected windows, and weighted fusion is performed in combination with the degree of chaos of the corresponding-scale images to obtain an enhanced CT image. The present invention improves the effect of image enhancement by obtaining an accurate window size during image equalization processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the accompanying drawings required for the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0036] Figure 1 It is a flowchart of a method for enhancing a liver CT image provided by an embodiment of the present invention;

[0037] Figure 2 It is a flowchart of a method for obtaining the degree of change in high-frequency information provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of the method and system for enhancing a liver CT image proposed according to the present invention. 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.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs.

[0040] The following specifically describes the specific solutions of the liver CT image enhancement method and system provided by the present invention in conjunction with the accompanying drawings.

[0041] Please refer to Figure 1 , which shows a flowchart of a liver CT image enhancement method provided by an embodiment of the present invention. The specific method includes:

[0042] Step S1: Obtain a CT image of the liver.

[0043] In an embodiment of the present invention, in order to accurately analyze the liver region, first, a CT scanner is used to obtain a CT image of the liver at the cross-section of the patient's liver region for further preprocessing and analysis. It should be noted that the processing method for each CT image is the same and will not be elaborated here. Only one CT image will be used as an example hereinafter.

[0044] Considering the noise introduced by the device, environment, or scanning process, in order to facilitate the subsequent image processing process, preprocessing operations are performed on the obtained CT image to enhance the image quality. It should be noted that image preprocessing operations are a well-known technical means in the art and can be specifically set according to the specific implementation scenario. In an embodiment of the present invention, bilateral filtering is used for preprocessing to balance denoising and retain edge information, which can highlight the contours and details of the image, making the image clearer. Then, the image is linearly normalized to unify the contrast and brightness differences between different images. The specific means are well-known technical means in the art and will not be elaborated here.

[0045] Step S2: Obtain the connected regions of the CT image according to the gray-scale distribution of the pixel points on the CT image; obtain the initial window of each connected region according to the morphological characteristics of each connected region; obtain the density change degree of the pixel points in each initial window according to the density distribution of the pixel points in each initial window.

[0046] Due to the complexity of the internal organizational structure of the human body, the gray-scale distribution in the CT image often shows non-uniformity, and there are significant differences in the gray-scale values between different tissues. Through connected region analysis, different organizational structures in the CT image can be identified, reducing the interference of noise on the analysis, which is helpful for subsequent separate processing and analysis of each region. Obtain the connected regions of the CT image according to the gray-scale distribution of the pixel points on the CT image.

[0047] Preferably, in an embodiment of the present invention, the method for obtaining the connected regions includes:

[0048] Perform CANNY edge detection on the CT image to obtain the edge curve in the CT image, and use the area enclosed by the closed edge curve as the connected region.

[0049] It should be noted that the specific CANNY edge detection is a well-known technical means for those skilled in the art and will not be elaborated here.

[0050] The shape and size of the liver are important factors in determining the analysis window. Considering that the liver shape is relatively regular, oval or circular, analyze the morphological characteristics of the connected region. If the liver is large and has a normal shape, a larger window can be selected, which helps in global analysis; if the liver is small, has complex structural tissues or local lesions, a smaller window can be selected for more precise detail analysis; according to the morphological characteristics of each connected region, obtain the initial window for each connected region.

[0051] Preferably, in an embodiment of the present invention, the method for obtaining the initial window includes:

[0052] Obtain the square of the number of edge pixel points in each connected region as the edge pixel square number; obtain the ratio of the number of all pixel points and the edge pixel square number in each connected region as the first morphological coefficient; obtain the product of the preset ratio parameter and the first morphological coefficient as the shape factor;

[0053] It should be noted that the number of edge pixel points reflects the perimeter of the connected region, and the number of all pixel points reflects the area of the connected region. Considering that when the lung region is a standard circle, the ratio of the square of the perimeter to the area is 4π. In the embodiments of the present invention, in order to evaluate the shape factor and reflect the circular similarity of the connected region, the preset ratio parameter is 4π; among them, when the perimeter is fixed, the larger the area corresponding to the circle, the smaller the ratio of the square of the perimeter to the area, that is, the first morphological coefficient has a maximum value. Therefore, the larger the first morphological coefficient, the larger the shape factor, the closer the shape of the connected region is to the standard circle, and the more regular the corresponding liver region is.

[0054] In an embodiment of the present invention, for any connected region, the acquisition formula of the shape factor is expressed as:

[0055] ;

[0056] Wherein, represents the shape factor of the connected region; represents the number of all pixel points in the connected region, that is, the area of the connected region; represents the number of edge pixel points of the connected region, that is, the perimeter of the connected region; represents the ratio of the number of all pixel points and the edge pixel square number in the connected region, that is, the first morphological coefficient.

[0057] If the shape factor of the connected component is greater than the preset factor threshold, set the initial window corresponding to the connected component to the preset first window; otherwise, set the initial window corresponding to the connected component to the preset second window. The preset first window is larger than the preset second window. The initial window is a square region with equal width centered on the centroid of the connected component.

[0058] It should be noted that, in an embodiment of the present invention, the preset factor threshold is 0.5, the size of the preset first window is 50 50, and the size of the preset second window is 30 30; in other embodiments of the present invention, the preset factor threshold, the preset first window, and the preset second window can be specifically set according to specific situations, and will not be limited and elaborated herein.

[0059] The CT image reflects the attenuation degree of the radiation intensity when the radiation passes through the body. Since human organs or tissues are composed of various material components and different densities, the densities of different parts of the human body are different, the linear absorption degrees of the rays are different, and the resulting radiation responses are different. Therefore, by analyzing the density in each initial window in the image, the complexity of the density distribution of the pixel points in the local window is determined; according to the density distribution of the pixel points in each initial window on the CT image, the density change degree of each initial window is obtained.

[0060] Preferably, in an embodiment of the present invention, the method for obtaining the density change information includes:

[0061] Obtain the HU value of each pixel point on the CT image;

[0062] Obtain the mean value of the ratio between the HU values of different pixel points and the preset liver HU value, and perform normalization, which is used as the density change degree of each initial window.

[0063] In an embodiment of the present invention, the formula for obtaining the density change degree is expressed as:

[0064] ;

[0065] Wherein, represents the density change degree of the th initial window; represents the number of pixel points in the th initial window; represents the th pixel point in the th initial window; represents the preset liver HU value; represents the normalization function.

[0066] In the formula for the density change degree, Indicates calculating the difference between the HU value of the pixel in the th initial window and the preset liver HU value, reflecting the degree to which the th pixel in each initial window belongs to the liver region; Indicates calculating the average difference between the HU values of all pixels in the th initial window and the preset liver HU value. The larger the average difference, the greater the difference between the HU value of the pixel and the preset liver HU value, the less it belongs to the lung region, the more complex the information distribution, and the greater the density change degree.

[0067] It should be noted that in the embodiments of the present invention, the HU value is used to describe the absorption of rays by different tissues and reflects its density performance on the CT image. The method for obtaining the HU value is to process the CT image in a specific format through professional medical image processing software and then convert the pixel values in the CT image into HU values by using the windowing method. The specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0068] It should be noted that in order to evaluate the correlation between the initial window and the liver region, in an embodiment of the present invention, the preset liver HU value is pre-obtained by the implementer according to relevant professional materials, that is, for the standard liver HU value range between 45 and 65, the average value is calculated as the corresponding preset liver HU value.

[0069] Step S3: Obtain the multi-scale images corresponding to the CT image; obtain the high-frequency information change degree of each initial window according to the frequency domain distribution characteristics corresponding to each initial window between different scale images; obtain the window correction coefficient of each initial window according to the density change degree and the high-frequency information change degree of each initial window; correct each initial window according to the window correction coefficient to obtain the corrected window of each initial window.

[0070] Since liver CT images usually include multiple structures such as the liver itself, blood vessels, bile ducts, and surrounding soft tissues, and the contrast of different regions or structures is different, single-scale image processing will ignore many detailed features. Therefore, obtain the multi-scale images corresponding to the CT image; it should be noted that in an embodiment of the present invention, the method for obtaining the multi-scale images includes: obtaining the multi-scale images of the CT image by using a Gaussian pyramid.

[0071] Among them, the image pyramid is a technology that forms multiple resolution levels by gradually downsampling the image and applying Gaussian blur. By constructing multi-scales at different resolutions, the information features of the CT image at different scale dimensions can be captured.

[0072] It should be noted that in an embodiment of the present invention, in order to make the images consistent in a certain standard or feature for subsequent processing or analysis, the interpolation method is used to normalize the images at different scales so that the multi-scale images have a unified size. The specific image pyramid and interpolation method are well-known technical means to those skilled in the art and will not be elaborated here.

[0073] The frequency domain distribution characteristics can reflect the energy distribution and relative importance of different frequency components in the image. In liver CT images, high-frequency information corresponds to the detailed parts in the image, such as the edge information between liver tissue and other structures like blood vessels and bile ducts. Due to the change in scale, the high-frequency components of the image will gradually be blurred, and thus the low-frequency components will dominate. By analyzing the frequency distribution characteristics at different scales, the image data within the initial window can be better understood and processed, and then the change situation of the high-frequency information can be evaluated. According to the frequency domain distribution characteristics of the initial windows corresponding to each same position among the images at different scales, the change degree of the high-frequency information of each initial window is obtained.

[0074] Preferably, in an embodiment of the present invention, for the method of obtaining the change degree of high-frequency information, please refer to Figure 2 , which shows a flowchart of a method for obtaining the change degree of high-frequency information, including:

[0075] Step S301: For any scale image, obtain the frequency domain image of each initial window.

[0076] Through the frequency domain image, it is easier to identify and analyze the high-frequency and low-frequency components in the image.

[0077] It should be noted that in the embodiment of the present invention, the fast Fourier transform is adopted to convert each scale image from the spatial domain to the frequency domain. The specific fast Fourier transform is a well-known technical means to those skilled in the art and will not be elaborated here.

[0078] Step S302: Obtain the sum of the amplitudes of all high-frequency information in each frequency domain image as the first amplitude; obtain the sum of all frequency domain amplitudes in each frequency domain image as the second amplitude; obtain the ratio of the first amplitude to the second amplitude as the high-frequency ratio.

[0079] High-frequency information reflects the parts with drastic changes such as edges, details, and noise in the frequency domain image. The first amplitude reflects the content of high-frequency components in the initial window in the frequency domain, and the second amplitude reflects the total energy or total information amount in the initial window in the frequency domain. The high-frequency ratio is an index to measure the relative importance of high-frequency components in the window, reflecting the proportion of high-frequency information such as edges, details, and noise in the image relative to the overall information. The larger the sum of the amplitudes of high-frequency information, the richer the edges and details in the image, or the higher the noise level, and the more targeted analysis is required.

[0080] Preferably, in an embodiment of the present invention, the method for obtaining high-frequency information includes:

[0081] For any frequency-domain image, obtain the relative distance between the pixel points with non-zero gray values and the center point of the frequency-domain image, construct a distance histogram of the relative distances corresponding to all pixel points with non-zero gray values, and use the Otsu method to segment the distance histogram to obtain the segmentation region of the distance histogram;

[0082] Select the one with the largest average relative distance in the segmentation region, and use the corresponding pixel points as the high-frequency information in the spectral image.

[0083] It should be noted that in some implementation methods of the present invention, the relative distance can be obtained by using distance measurement methods such as Euclidean distance or Manhattan distance. The specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0084] Step S303: According to the difference in the high-frequency ratio corresponding to each initial window at the same position between different adjacent scale images, obtain the change degree of high-frequency information for each initial window. The difference in the high-frequency ratio is positively correlated with the change degree of high-frequency information.

[0085] Among them, the difference in the high-frequency ratio reflects the change in the high-frequency information content of each initial window on different adjacent scale images. The greater the difference in the high-frequency ratio, the more different the characteristics of high-frequency information between adjacent scale images, and the greater the change degree of high-frequency information, indicating that there is more edge information of liver tissue or other structures in the initial window.

[0086] In an embodiment of the present invention, the acquisition formula for the change degree of high-frequency information is expressed as:

[0087] ;

[0088] Among them, represents the change degree of high-frequency information of the th initial window; represents the sum of the amplitudes of high-frequency information in the frequency-domain image corresponding to the th initial window on the th scale image; represents the sum of all frequency-domain amplitudes in the frequency-domain image corresponding to the th initial window on the th scale image; represents the sum of the amplitudes of high-frequency information in the frequency-domain image corresponding to the th initial window on the th scale image; represents the sum of the amplitudes of high-frequency information in the frequency-domain image corresponding to the th initial window on the The sum of all frequency domain amplitudes corresponding to an initial window; m represents the number of scale images; represents a normalization function.

[0089] In the formula for the degree of change in high-frequency information, represents calculating the th initial window on the th scale image, which is the ratio of the sum of the amplitudes of high-frequency information in the corresponding frequency domain image to the sum of all frequency domain amplitudes, that is, the high-frequency ratio corresponding to the th initial window on the th scale image. The larger the high-frequency ratio, the greater the sum of the amplitudes of high-frequency information, and the more high-frequency information is contained in the initial window; represents calculating the difference in the high-frequency ratios corresponding to the th scale image and the th scale image for the th initial window. The greater the difference, the less close the high-frequency ratios are, and the greater the change in the high-frequency information represented.

[0090] The degree of density change reflects the complexity of the detailed information within the initial window. The greater the degree of density change, the more complex the detailed information contained in the initial window, and the more it needs to be enhanced with emphasis. The degree of change in high-frequency information reflects the degree of information change within the initial window. The higher the degree of information change, the more important the information representation, and the more it needs to be adjusted for the window. According to the degree of density change and the degree of change in high-frequency information of each initial window, the window correction coefficient of each initial window is obtained.

[0091] Preferably, in an embodiment of the present invention, the method for obtaining the window correction coefficient includes:

[0092] Fuse the degree of density change and the degree of change in high-frequency information of each initial window to obtain the window correction coefficient corresponding to the initial window.

[0093] In some embodiments of the present invention, the degree of density change and the degree of change in high-frequency information are fused by multiplication or addition. The specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0094] By obtaining the window correction coefficient, the content of detailed information within the window can be reflected, and the size of the window can be reselected; if the window size is set too small, although local detailed information can be better captured, global information may be ignored, resulting in poor enhancement effects; while if the window size is set too large, although global information can be better considered, more noise and computational complexity may be introduced; each initial window is corrected according to the window correction coefficient to obtain the corrected window of each initial window.

[0095] Preferably, in an embodiment of the present invention, the method for obtaining the correction window includes:

[0096] Obtain the difference between the positive integer 1 and the window correction coefficient as the adjustment weight;

[0097] Obtain the product of the adjustment weight and the initial size of the initial window, calculate the sum of the product result and the initial size as the correction size, and obtain the correction window.

[0098] In an embodiment of the present invention, the formula for the correction size is expressed as:

[0099] ;

[0100] where represents the correction size of the th initial window; represents the initial size of the th initial window; represents the window correction coefficient of the th initial window.

[0101] In the formula for the correction size, represents the difference between the positive integer 1 and the window correction coefficient, that is, the adjustment weight. The larger the window correction coefficient, the more detailed information is included in the window, the greater the possibility of including the edge information of the liver tissue part, and the smaller the adjustment of the initial size, which is convenient for local detail discrimination; the smaller the window correction coefficient, the more the window is located in the internal area of the liver tissue, the less detailed information is included, and the greater the adjustment of the initial size, which helps to consider the global enhancement effect.

[0102] Step S4: Perform adaptive histogram equalization on the images of different scales according to the correction window, and perform weighted fusion in combination with the degree of chaos of the corresponding scale images to obtain the enhanced CT image.

[0103] If the window in the adaptive histogram equalization is too large or too small, there may be over-enhancement or weakening of the contrast in some regions of the image, resulting in the loss of important information. By obtaining the correction window, different regions with different detail features can be processed more flexibly. In the weighted fusion process, different weights are assigned according to the degree of chaos of the corresponding scale images, which can ensure that images with rich details and high contrast are more retained and emphasized in the fusion result; therefore, perform adaptive histogram equalization on the images of different scales according to the correction window, and perform weighted fusion in combination with the degree of chaos of the corresponding scale images to obtain the enhanced CT image.

[0104] It should be noted that, in an embodiment of the present invention, the degree of chaos is represented by calculating the information entropy, which can reflect the richness of detailed information in the image. The larger the information entropy, the greater the degree of chaos and the more detailed information; the smaller the information entropy, the smaller the degree of chaos and the less detailed information. The specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0105] In another embodiment of the present invention, the method for obtaining an enhanced CT image includes: obtaining the ratio of the degree of chaos of each scale image to the sum of the degrees of chaos of all scale images as the fusion weight of each scale image; weighting the scale image after adaptive histogram equalization based on the fusion weight of each scale image, and fusing all scale images to obtain an enhanced CT image. Among them, the larger the information entropy of the scale image, the more detailed information it contains, and the more details need to be retained, and the larger the fusion weight. By comprehensively considering the information volume and detailed information of different scale images, a clearer and more natural enhanced CT image can be obtained, and the detailed information in the liver CT image can be better displayed.

[0106] It should be noted that the specific adaptive histogram equalization is a well-known technical means to those skilled in the art and will not be elaborated here.

[0107] In summary, the present invention obtains the initial window of each connected domain according to the morphological characteristics of each connected domain in the CT image; obtains the degree of density change of each initial window according to the density distribution of the pixel points in each initial window on the CT image; obtains the multi-scale image corresponding to the CT image, and obtains the degree of change of the high-frequency information of each initial window according to the frequency domain distribution characteristics of the initial windows at the same position corresponding to different scale images; further obtains the window correction coefficient of each initial window, corrects each initial window, and obtains the corrected window of each initial window; performs adaptive histogram equalization on different scale images according to the corrected window, and performs weighted fusion in combination with the degree of chaos of the corresponding scale image to obtain an enhanced CT image. The present invention improves the effect of image enhancement by obtaining the accurate window size during image equalization processing.

[0108] The present invention also proposes a liver CT image enhancement system, including 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 any one of the liver CT image enhancement methods are implemented.

[0109] It should be noted that: the above-mentioned sequence of embodiments of the present invention is only for description and does not represent the superiority or inferiority 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.

[0110] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the key point of each embodiment is to illustrate the differences from other embodiments.

Claims

1. A liver CT image enhancement method, characterized in that: The method comprises: Obtain CT images of the liver; The connected domain of the CT image is obtained according to the grayscale distribution of the pixels on the CT image; the initial window of each connected domain is obtained according to the morphological characteristics of each connected domain; the density change degree of each initial window is obtained according to the density distribution of the pixels in each initial window on the CT image; Obtain a multi-scale image corresponding to the CT image; obtain the degree of change of high-frequency information of each initial window according to the frequency domain distribution characteristics of each initial window at the same position between the different-scale images; obtain a window correction coefficient of each initial window according to the degree of change of density and the degree of change of high-frequency information of each initial window; correct each initial window according to the window correction coefficient to obtain a corrected window of each initial window; Adaptive histogram equalization is performed on images of different scales according to the correction window, and weighted fusion is performed in combination with the degree of confusion of the images of corresponding scales to obtain an enhanced CT image.

2. A liver CT image enhancement method according to claim 1, characterized in that: The method for obtaining the connected domain includes: CANNY edge detection is performed on the CT image to obtain the edge curves in the CT image, and the independent areas surrounded by all closed edge curves are regarded as connected domains.

3. A liver CT image enhancement method according to claim 1, characterized in that: The method for obtaining the initial window includes: Obtaining the square of the number of edge pixels in each connected domain as the number of square edge pixels; obtaining the ratio of the number of all pixels in each connected domain to the number of square edge pixels as the first morphological coefficient; obtaining the product of a preset ratio parameter and the first morphological coefficient as a shape factor; If the shape factor of the connected domain is greater than the preset factor threshold, the initial window of the corresponding connected domain is set to the preset first window. Otherwise, the initial window of the corresponding connected domain is set to the preset second window. The preset second window is larger than the preset first window. The initial window is a square area of ​​equal width centered on the centroid of the connected domain.

4. The method for enhancing liver CT images according to claim 1, characterized in that: The method for obtaining the density variation degree includes: Get the HU value of each pixel on the CT image; The mean value of the difference between the HU values ​​of different pixel points and the preset liver HU value was obtained as the density change degree of each initial window.

5. The method for enhancing liver CT images according to claim 1, characterized in that: The method for obtaining the degree of change of the high-frequency information includes: For any scale image, obtain the frequency domain image of each initial window; The sum of the amplitudes of all high-frequency information in each frequency domain image is obtained as a first amplitude; the sum of the frequency domain amplitudes in each frequency domain image is obtained as a second amplitude; and the ratio of the first amplitude to the second amplitude is obtained as a high-frequency ratio; According to the difference in high-frequency ratios corresponding to each initial window at the same position between images of different adjacent scales, the degree of change of high-frequency information of each initial window is obtained, and the difference in high-frequency ratios is positively correlated with the degree of change of high-frequency information.

6. A liver CT image enhancement method according to claim 1, characterized in that: The method for obtaining the high-frequency information comprises: For any frequency domain image, the relative distance between the pixel point with gray value not equal to 0 and the center point of the frequency domain image is obtained, and a distance histogram corresponding to the relative distance of all the pixel points with gray value not equal to 0 is constructed. The distance histogram is segmented using the Otsu method to obtain the segmented area of ​​the distance histogram. The largest relative distance mean in the segmented area is selected, and the corresponding pixel point is used as the high-frequency information in the spectrum image.

7. The method for enhancing liver CT images according to claim 1, characterized in that: The method for obtaining the window correction coefficient includes: The density change degree and high-frequency information change degree of each initial window are fused to obtain the window correction coefficient corresponding to the initial window.

8. The method for enhancing liver CT images according to claim 1, characterized in that: The method for obtaining the correction window includes: Obtain the difference between the positive integer 1 and the window correction coefficient as the adjustment weight; The product of the adjustment weight and the initial size of the initial window is obtained, and the sum of the product result and the initial size is calculated as the revised size to obtain the revised window.

9. The method for enhancing liver CT images according to claim 1, characterized in that: The method for acquiring the multi-scale image comprises: Gaussian pyramid is used to obtain multi-scale images corresponding to CT images.

10. A liver CT image enhancement 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 liver CT image enhancement method as described in any one of claims 1 to 9 are implemented.

Images