A method for enhancing lung CT images

Abstract

The present invention relates to the technical field of image enhancement processing, and particularly relates to a method for enhancing lung CT images, including: acquiring lung CT images, lung target regions, and regions to be enhanced; analyzing the correlation of the gray-scale extension trends between pixel points in the region to be enhanced based on the gray-scale distribution within the neighborhood of each pixel point in the region to be enhanced and the pixel point distribution in the lung target region, so as to obtain the extension similarity degree between every two pixel points in the region to be enhanced; based on the pixel point distribution in the gray-scale extension direction of each pixel point in the region to be enhanced and the position distribution between other pixel points and the corresponding gray-scale extension direction, combining the extension similarity degree to obtain the comprehensive similarity degree between every two pixel points in the region to be enhanced; adjusting the gray-scale value of each pixel point according to the comprehensive similarity degree between each pixel point and other pixel points in the region to be enhanced to obtain the enhanced image of the lung CT. The present invention has a good image enhancement effect on lung CT images.

Description

Technical Field

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

[0002] In the medical field, lung CT images are important tools for diagnosing and treating lung diseases. Traditional lung CT images have limitations in terms of clarity and noise control, which cause certain difficulties for doctors during the diagnosis and treatment processes. Especially in the field of lung treatments such as radiotherapy and radiation therapy, accurate image information is crucial for assisting doctors in formulating treatment plans.

[0003] In lung CT images, due to the low contrast between important tissues such as blood vessels and other lung tissues, in practice, it is necessary to enhance lung CT images to more intuitively and clearly display lung tissues for doctors to observe. However, existing technologies mainly enhance CT images by analyzing the pixel gray-scale distribution, and do not combine the characteristic extension directions of tissues such as blood vessels that are densely distributed in lung CT images, resulting in poor enhancement effects for the densely distributed blood vessel parts in lung CT images. Summary of the Invention

[0004] In order to solve the technical problem that existing methods have poor enhancement effects for the densely distributed blood vessel parts in lung CT images, the purpose of the present invention is to provide a method for enhancing lung CT images, and the specific technical solutions adopted are as follows:

[0005] Obtain a lung CT image, and perform segmentation preprocessing on the lung CT image to obtain a lung target region and a region to be enhanced;

[0006] According to the gray-scale distribution of each pixel point in the region to be enhanced within the neighborhood range and the pixel point distribution of the lung target region, analyze the relevance of the gray-scale extension trends between pixel points in the region to be enhanced, and obtain the extension similarity degree between every two pixel points in the region to be enhanced;

[0007] According to the distribution of pixel points in the gray-scale extension direction of each pixel point in the region to be enhanced and the position distribution between other pixel points and the corresponding gray-scale extension direction, and combining the extension similarity degree, obtain the comprehensive similarity degree between every two pixel points in the region to be enhanced;

[0008] According to the comprehensive similarity degree between each pixel point and other pixel points in the region to be enhanced, adjust the gray-scale value of the pixel point to obtain an enhanced image of the lung CT.

[0009] Preferably, based on the gray - level distribution of each pixel point in the area to be enhanced within the neighborhood range and the pixel - point distribution of the lung target area, analyze the correlation of the gray - level extension trend among the pixel points in the area to be enhanced, and obtain the extension similarity degree between every two pixel points in the area to be enhanced. Specifically, it includes:

[0010] Based on the gray - level distribution of each pixel point in the area to be enhanced within the neighborhood range and the pixel - point distribution of the lung target area, perform region growing on each pixel point in the area to be enhanced to obtain the gray - level feature area of each pixel point in the area to be enhanced;

[0011] Based on the path distribution of each pixel point in the area to be enhanced from the corresponding gray - level feature area to the lung target area, obtain the gray - level extension path of each pixel point in the area to be enhanced;

[0012] Based on the gray - level distribution difference, the chain - code information difference of the pixel points, and the length difference of the gray - level extension paths of the pixel points on the gray - level extension paths of every two pixel points in the area to be enhanced, obtain the extension similarity degree between every two pixel points in the area to be enhanced.

[0013] Preferably, the method for obtaining the gray - level feature area is specifically as follows:

[0014] Take each pixel point in the area to be enhanced as an initial seed point respectively, and perform region growing according to the set region - growing rule to obtain the gray - level feature area corresponding to each pixel point in the area to be enhanced;

[0015] Among them, the region - growing rule is: if the difference between the gray - level value of the initial seed point and the gray - level values of the pixel points in its neighborhood is less than or equal to the preset difference threshold, then take the pixel point corresponding to the minimum gray - level value in the neighborhood of the initial seed point as the new seed point for growth until there are pixel points in the lung target area within the neighborhood range of the growing seed point, or the difference between the gray - level value of the growing seed point and the gray - level values of the pixel points in its neighborhood is greater than the difference threshold, then stop growing.

[0016] Preferably, the step of obtaining the gray - level extension path of each pixel point in the area to be enhanced based on the path distribution of each pixel point in the area to be enhanced from the corresponding gray - level feature area to the lung target area specifically includes:

[0017] Take any pixel point in the area to be enhanced as the selected pixel point, obtain the pixel point with the minimum distance from the gray - level feature area of the selected pixel point to the lung target area as the feature pixel point, and within the gray - level feature area of the selected pixel point, take the shortest path between the selected pixel point and the corresponding feature pixel point as the gray - level extension path of the selected pixel point.

[0018] Preferably, obtaining the extension similarity degree between every two pixel points in the area to be enhanced according to the gray - level distribution difference of pixel points on the gray - level extension path between every two pixel points in the area to be enhanced, the chain - code information difference of pixel points, and the length difference of the gray - level extension path, specifically includes:

[0019] Obtaining the 8 - chain - code sequence of the gray - level extension path of each pixel point in the area to be enhanced; respectively denoting any two different pixel points in the area to be enhanced as the first pixel point and the second pixel point;

[0020] Based on the difference between the mean gray - level values of all pixel points on the gray - level extension paths of the first pixel point and the second pixel point, determining the gray - level difference factor;

[0021] Based on the difference between the mean values of all chain - code values in the 8 - chain - code sequences corresponding to the first pixel point and the second pixel point, determining the chain - code difference factor;

[0022] Based on the length difference between the gray - level extension paths of the first pixel point and the second pixel point, determining the path difference factor;

[0023] Performing a negative - correlation process on the product of the gray - level difference factor, the chain - code difference factor, and the path difference factor to obtain the extension similarity degree between the first pixel point and the second pixel point.

[0024] Preferably, obtaining the comprehensive similarity degree between every two pixel points in the area to be enhanced according to the distribution of pixel points in the gray - level extension direction of each pixel point in the area to be enhanced and the position distribution between other pixel points and the corresponding gray - level extension direction, combined with the extension similarity degree, specifically includes:

[0025] According to the quantity distribution of other pixel points outside the gray - level extension path of each pixel point in the area to be enhanced and the distance fluctuation between other pixel points and the gray - level extension path, combined with the length distribution of the gray - level extension path, obtaining the representative feature index of each pixel point in the area to be enhanced;

[0026] According to the representative feature indexes of every two pixel points in the area to be enhanced, adjusting the extension similarity degree between every two pixel points to obtain the comprehensive similarity degree between every two pixel points in the area to be enhanced.

[0027] Preferably, the method for obtaining the representative feature index of each pixel point in the area to be enhanced is specifically as follows:

[0028] Within the gray - level feature region of the selected pixel point, calculating the variance of the shortest distances between all other pixel points except the gray - level extension path of the selected pixel point and the gray - level extension path to obtain the first coefficient;

[0029] Within the grayscale feature region of the selected pixel point, obtain the number of all other pixel points except the grayscale extension path of the selected pixel point to obtain a second coefficient;

[0030] According to the first coefficient, the second coefficient, and the length of the grayscale extension path of the selected pixel point, obtain a representative feature index of the selected pixel point. The length of the grayscale extension path has a positive correlation with the representative feature index, and both the first coefficient and the second coefficient have a negative correlation with the representative feature index.

[0031] Preferably, adjusting the extension similarity degree between every two pixel points according to the representative feature indexes of every two pixel points in the region to be enhanced to obtain the comprehensive similarity degree between every two pixel points in the region to be enhanced specifically includes:

[0032] Take the product of the representative feature index of the first pixel point, the representative feature index of the second pixel point, and the extension similarity degree between the first pixel point and the second pixel point as the comprehensive similarity degree between the first pixel point and the second pixel point.

[0033] Preferably, adjusting the grayscale value of the pixel point according to the comprehensive similarity degree between each pixel point in the region to be enhanced and other pixel points to obtain the enhanced image of the lung CT specifically includes:

[0034] Take any pixel point in the region to be enhanced as the target pixel point, take the pixel points except the target pixel point in the region to be enhanced as the reference pixel points, arrange the reference pixel points in descending order according to the comprehensive similarity degree between the target pixel point and each reference pixel point, and obtain a preset number of reference pixel points as the control pixel points of the target pixel point according to the arrangement order;

[0035] Use the comprehensive similarity degree between the target pixel point and each control pixel point to perform weighted averaging on the grayscale value of each control pixel point to obtain the enhanced grayscale value of the target pixel point;

[0036] The enhanced grayscale values of each pixel point in the region to be enhanced constitute the enhanced image of the lung CT.

[0037] Preferably, the preprocessing of the lung CT image for segmentation to obtain the lung target region and the region to be enhanced specifically includes:

[0038] Use the maximum inter-class variance method to perform region segmentation on the lung CT image, take the region with a grayscale value greater than the segmentation threshold as the lung target region, and take the region with a grayscale value less than or equal to the segmentation threshold as the region to be enhanced.

[0039] The embodiments of the present invention have at least the following beneficial effects:

[0040] The present invention first performs a preliminary regional division operation on the collected lung CT images, and preliminarily screens out some relatively blurred partial regions that need to be enhanced, providing a data basis for the subsequent feature analysis process. Then, on the one hand, for the gray-scale distribution of pixel points within the neighborhood range and the pixel distribution within the lung target region, the relevance and similarity of the gray-scale extension features of pixel points in the region to be enhanced are analyzed, and the degree of extension similarity between two pixel points is initially constructed, which characterizes the similarity of the gray-scale extension rules between two pixel points in the corresponding region. Further, on the basis of the similarity of the gray-scale extension rules initially analyzed, on the second hand, in combination with the pixel position distribution other than the gray-scale extension of the pixel points, the degree of similarity is comprehensively characterized, which can more accurately reflect the feature similarity situation between pixel points in the region to be enhanced. Finally, by combining the gray-scale values of each pixel point with those of other pixel points with relatively similar features, the gray-scale value of the pixel point is adjusted, which can effectively enhance the relatively blurred details in the image, and fully consider and analyze the feature of the blood vessel extension rule of the lung, resulting in a better image enhancement effect for the lung CT image. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0042] Figure 1 It is a flowchart of the steps of a method for enhancing lung CT images provided by the present invention;

[0043] Figure 2 It is a flowchart of the steps of a method for obtaining the degree of extension similarity between every two pixel points in the region to be enhanced provided by the present invention;

[0044] Figure 3 It is a flowchart of the steps of a method for obtaining the comprehensive similarity degree between every two pixel points in the region to be enhanced provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manner, structure, features and effects of a method for enhancing lung CT images 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.

[0046] 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.

[0047] The specific scheme of the lung CT image enhancement method provided by the present invention is described in detail below with reference to the accompanying drawings.

[0048] See also Figure 1 , which shows a flowchart of a method for enhancing lung CT images provided by an embodiment of the present invention, the method comprising the following steps:

[0049] Step S100, acquiring a lung CT image, and performing segmentation preprocessing on the lung CT image to obtain a lung target area and an area to be enhanced.

[0050] In the case of electromagnetic or other noise interference, the presence of noise in lung CT images will cause aliasing between the detailed information in the lungs and the background information, thereby blurring or hiding the information in the CT image and causing the loss of image detail information. Therefore, it is necessary to further enhance the more detailed blood vessels in the lung CT image.

[0051] It should be noted that in the human lungs, the main blood vessels are the pulmonary artery and pulmonary vein, bronchial artery and bronchial vein, and pulmonary capillaries. Among them, the pulmonary artery trunk starts from the right ventricle and divides into two pulmonary arteries below the aortic arch. The pulmonary artery runs along with the bronchi at all levels, and finally forms a capillary network distributed on the alveolar wall. At the same time, the thickness of the blood vessels gradually decreases from the pulmonary artery to the capillaries.

[0052] Under normal circumstances, the pulmonary arteries and bronchial arteries in lung CT images are thicker and more sparsely distributed, so they are clearer and easier to distinguish. However, the pulmonary capillaries are thinner and more densely distributed, so they are easily affected by noise and blurred, making them more difficult to distinguish.

[0053] Capillaries usually extend gradually from the pulmonary artery to the bronchial artery and then to the capillaries. Therefore, the distribution of blood vessels has a distribution pattern in the extension direction, and the overall distribution direction of capillaries in the lungs is also distributed along the extension direction of the blood vessels, that is, from the middle part of the lungs to the surrounding areas. Therefore, when enhancing the lung CT images, the lung CT images can be preliminarily divided and the parts with low contrast and unclearness can be preliminarily screened out to further analyze the extension distribution pattern of the blood vessels.

[0054] Specifically, first, a lung CT image is obtained. In order to better perform the image analysis process, the lung CT image in this embodiment is a grayscale image. Then, the lung CT image is subjected to segmentation preprocessing to obtain a lung target region and a region to be enhanced. The lung target region is the relatively clear target part in the lung CT image, and the region to be enhanced is the relatively blurred part to be enhanced in the lung CT image.

[0055] More specifically, the maximum inter-class variance method is used to perform region segmentation on the lung CT image, that is, the segmentation threshold of the lung CT image is obtained by using the maximum variance method, and the lung CT image is segmented by the segmentation threshold, and the segmentation result is preprocessed, such as morphological erosion operation, to eliminate local isolated segmentation regions, and finally the lung target region and the region to be enhanced are obtained. Among them, specifically, the region with a gray value greater than the segmentation threshold is used as the lung target region, and the region with a gray value less than or equal to the segmentation threshold is used as the region to be enhanced.

[0056] Step S200: According to the gray distribution of each pixel point in the region to be enhanced within the neighborhood range and the pixel distribution of the lung target region, analyze the correlation of the gray extension trend between the pixel points in the region to be enhanced, and obtain the extension similarity degree between every two pixel points in the region to be enhanced.

[0057] In the actual distribution of the region to be enhanced, it contains relatively blurred and difficult-to-distinguish capillary parts and background parts. Capillaries have a certain extension rule in the lung region and will have a certain connection relationship with the lung target part. Based on this, in order to better enhance the vascular characteristics of the blurred part to distinguish the background and target blood vessels, it is first necessary to analyze the distribution of the extension rule based on the gray value of each pixel point in the region to be enhanced, determine the gray extension direction at each pixel point position in this region, and further analyze the feature differences and feature correlation between the pixel points in this region based on the gray extension direction.

[0058] In this embodiment, as Figure 2 shown, the method for obtaining the extension similarity degree between every two pixel points in the region to be enhanced can be implemented by steps S201 to S203.

[0059] Step S201: According to the gray distribution of each pixel point in the region to be enhanced within the neighborhood range and the pixel distribution of the lung target region, perform region growing on each pixel point in the region to be enhanced to obtain the gray feature region of each pixel point in the region to be enhanced.

[0060] Specifically, each pixel point in the region to be enhanced is used as an initial seed point, and region growing is performed according to the set region growing rules to obtain the gray feature region corresponding to each pixel point in the region to be enhanced; the gray feature region contains all the previous seed points during the growth process of each pixel point according to the region growing rules.

[0061] Among them, the region growing rules are as follows: if the difference between the gray value of the initial seed point and the gray value of the pixel points in its neighborhood is less than or equal to the preset difference threshold, then the pixel point corresponding to the minimum gray value in the neighborhood of the initial seed point is used as a new seed point for growth until there are pixel points in the lung target region within the neighborhood range of the growing seed point, or the difference between the gray value of the growing seed point and the gray value of the pixel points in its neighborhood is greater than the difference threshold, and then the growth stops.

[0062] In this embodiment, the value of the difference threshold is 30, and the value of the neighborhood range is 8-neighborhood. In other embodiments, the implementer can set it according to the specific implementation scenario. More specifically, for any initial seed point, calculate the absolute value of the gray value difference between the initial seed point and the pixel points in the 8-neighborhood. When the absolute value of the gray value difference is less than or equal to 30, the pixel point corresponding to the minimum absolute value of the gray value difference in the 8-neighborhood of the initial seed point is used as a new seed point for growth. Further, analyze whether the gray value difference in the 8-neighborhood of the new seed point meets the threshold for region growing.

[0063] So far, after region growing for each pixel point in the region to be enhanced, the corresponding gray feature region is obtained, which characterizes the regional distribution of the gray extension at the position of each pixel point.

[0064] Step S202, obtain the gray extension path of each pixel point in the region to be enhanced according to the path distribution of each pixel point in the region to be enhanced from the corresponding gray feature region to the lung target region.

[0065] Considering that during the region growing process of the pixel points in the region to be enhanced, the seed points grow in the 8-neighborhood, and there are many extension directions, and the finally obtained growth region may not be just a linear region, but may also be a region with a certain area. Therefore, it is also necessary to further analyze the path distribution of the pixel points in the gray feature region of each pixel point in the region to be enhanced, and screen out the main extension line to characterize the gray extension direction at the position of the pixel point.

[0066] Specifically, take any pixel point in the region to be enhanced as the selected pixel point, obtain the pixel point with the smallest distance from the lung target region in the gray feature region of the selected pixel point as the feature pixel point, and in the gray feature region of the selected pixel point, take the shortest path between the selected pixel point and the corresponding feature pixel point as the gray extension path of the selected pixel point.

[0067] It should be noted that the method for obtaining the shortest path between two pixel points is a well-known technology, such as the A* algorithm, etc. The process will not be introduced here, and the implementer can select according to the specific implementation scenario. So far, the representation of the extension direction of each pixel point in the corresponding gray feature region in the region to be enhanced can be obtained, that is, the corresponding gray extension direction. In the gray extension direction, the feature pixel point is the end point of the path.

[0068] Step S203: According to the gray distribution difference of the pixel points on the gray extension path between every two pixel points in the region to be enhanced, the chain code information difference of the pixel points, and the length difference of the gray extension path, obtain the extension similarity degree between every two pixel points in the region to be enhanced.

[0069] In the region to be enhanced, if the pixel points belong to the same blood vessel part or the same background part, then there will be a certain similarity and correlation in the gray extension situations of these pixel points belonging to the same part. Based on the consideration of multiple aspects of features, the gray distribution, extension direction, and displacement amount distribution of the shortest paths in the gray feature regions of each pixel point in the region to be enhanced are relatively similar. By synthesizing the feature differences and feature similarity situations of every two pixel points in these aspects in the region to be enhanced, the similarity and correlation of every two pixel points in the extension feature law aspect can be quantitatively characterized.

[0070] In this embodiment, any two different pixel points in the region to be enhanced are taken as an example for illustration, that is, any two different pixel points in the region to be enhanced are respectively denoted as the first pixel point and the second pixel point. It can be understood that first, the 8-chain code sequence of the gray extension path of each pixel point in the region to be enhanced is obtained. The method for obtaining the 8-chain code sequence is a well-known technology and will not be introduced in detail here. The chain code value can represent the connection direction situation of the corresponding edge to a certain extent.

[0071] Specifically, based on the difference between the mean gray values of all pixel points on the gray extension paths of the first pixel point and the second pixel point, determine the gray difference factor; based on the difference between the mean values of all chain code values in the corresponding 8-chain code sequences of the first pixel point and the second pixel point, determine the chain code difference factor; based on the length difference between the gray extension paths of the first pixel point and the second pixel point, determine the path difference factor; perform a negative correlation process on the product of the gray difference factor, the chain code difference factor, and the path difference factor to obtain the extension similarity degree between the first pixel point and the second pixel point.

[0072] As a specific example, taking the x-th pixel point in the region to be enhanced as the first pixel point and the y-th pixel point in the region to be enhanced as the second pixel point, the calculation formula for the extension similarity degree between the first pixel point and the second pixel point can be specifically expressed as:

[0073]

[0074] Among them, represents the degree of extended similarity between the first pixel point and the second pixel point, x represents the x-th pixel point in the area to be enhanced, y represents the y-th pixel point in the area to be enhanced, and ; represents the average gray value of all pixel points on the gray extension path corresponding to the gray feature area of the first pixel point, represents the average gray value of all pixel points on the gray extension path corresponding to the gray feature area of the second pixel point; represents the average value of all chain code values in the 8-chain code sequence of the gray extension path corresponding to the gray feature area of the first pixel point, represents the average value of all chain code values in the 8-chain code sequence of the gray extension path corresponding to the gray feature area of the second pixel point; represents the total number of all pixel points on the gray extension path corresponding to the gray feature area of the first pixel point, represents the total number of all pixel points on the gray extension path corresponding to the gray feature area of the second pixel point, represents the exponential function with the natural constant e as the base.

[0075] represents the gray difference factor, which reflects the gray difference between two pixel points on the corresponding gray extension path; and both reflect the overall displacement of the edge on the gray extension path corresponding to the pixel point, represents the chain code difference factor, which reflects the edge direction difference between two pixel points on the corresponding gray extension path; represents the path difference factor, which reflects the length difference between two pixel points on the corresponding gray extension path.

[0076] The greater the difference between any two pixel points in these three aspects, the smaller the similarity and correlation between the corresponding two pixel points in terms of the gray extension law, and thus the smaller the value of the corresponding extended similarity degree. Based on this, negative correlation processing is performed using the negative exponential function. Among them, the extended similarity degree preliminarily characterizes the similarity and correlation between two pixel points in the direction of the gray extension law by analyzing the characteristic differences between two pixel points in three aspects.

[0077] Step S300, according to the distribution of pixel points in the gray extension direction of each pixel point in the area to be enhanced and the position distribution between other pixel points and the corresponding gray extension direction, combined with the extended similarity degree, obtain the comprehensive similarity degree between every two pixel points in the area to be enhanced.

[0078] The degree of extended similarity between every two pixel points in the preliminary analysis only considers the feature similarity on the gray-scale extension path of the pixel points within the area to be enhanced. Therefore, it is necessary to further analyze the distance distribution and quantity distribution of other pixel points besides the gray-scale extension path, and analyze whether the current gray-scale extension path has a high representative feature for the gray-scale feature area of the corresponding pixel points, and further adjust the correlation relationship and similarity relationship between every two pixel points.

[0079] Based on this, as Figure 3 shown, the method for obtaining the comprehensive similarity degree between every two pixel points in the area to be enhanced can be implemented by step S301 and step S302.

[0080] Step S301: According to the quantity distribution of other pixel points besides the gray-scale extension path of each pixel point in the area to be enhanced and the distance fluctuation between other pixel points and the gray-scale extension path, combined with the length distribution of the gray-scale extension path, obtain the representative feature index of each pixel point in the area to be enhanced.

[0081] Under normal circumstances, the distribution of blood vessels in the image generally shows a certain gray-scale distribution around the main extension direction of the area and the distribution area is relatively small. Based on this, when analyzing other pixel points besides the gray-scale extension path in the gray-scale feature area of the pixel points in the area to be enhanced, the fewer the distribution quantity, the clearer the main extension direction can express the gray-scale extension law of the pixel point location. The closer the pixel point location is to the gray-scale extension path, it indicates that there are some pixel points distributed in the relatively close part around the gray-scale extension path, which is more in line with the characteristic distribution phenomenon of the blood vessel part.

[0082] Based on this, combining features in multiple aspects, quantify the degree of feature manifestation of the gray-scale extension path of each pixel point in the gray-scale feature area. Specifically, within the gray-scale feature area of the selected pixel point, calculate the variance of the shortest distance between all other pixel points except the gray-scale extension path of the selected pixel point and the gray-scale extension path to obtain the first coefficient; within the gray-scale feature area of the selected pixel point, obtain the quantity of all other pixel points except the gray-scale extension path of the selected pixel point to obtain the second coefficient; according to the first coefficient, the second coefficient and the length of the gray-scale extension path of the selected pixel point, obtain the representative feature index of the selected pixel point. The length of the gray-scale extension path has a positive correlation with the representative feature index, and both the first coefficient and the second coefficient have a negative correlation with the representative feature index.

[0083] As a specific example, taking any pixel point in the area to be enhanced as an illustration, if the \(i\)-th pixel point in the area to be enhanced is taken as the selected pixel point, then the representative feature index of the \(i\)-th pixel point in the area to be enhanced, that is, the selected pixel point, can be expressed by the formula:

[0084]

[0085] Among them, represents the representative feature index of the \(i\)-th pixel point in the area to be enhanced, that is, the selected pixel point, and \(i\) represents the \(i\)-th pixel point in the area to be enhanced; represents the variance of the shortest distances from all other pixel points except the gray-scale extension path of the selected pixel point to the gray-scale extension path in the gray-scale feature area of the selected pixel point; represents the total number of all pixel points on the gray-scale extension path corresponding to the gray-scale feature area of the selected pixel point, that is, the path length; represents the total number of all other pixel points except the gray-scale extension path of the selected pixel point in the gray-scale feature area of the selected pixel point, represents the normalization function.

[0086] is the first coefficient, which reflects the degree of dispersion of the distance distribution of other pixel points to the current main extension direction in the gray-scale feature area of the selected gray-scale pixel point. is the second coefficient, which reflects the quantity distribution of other pixel points. The larger the values of both, the more discrete the distribution of pixel points in the non-main extension direction relative to the main extension direction in the gray-scale feature area, and the larger the quantity. Furthermore, it indicates that the current main extension direction is more difficult to characterize the gray-scale extension law of the gray-scale feature area, that is, the corresponding representativeness is worse. At the same time, the larger the value of, the more pixel representations there are on the main extension direction, and the more possible representative feature manifestations there are, and thus the larger the value of the representative feature index.

[0087] So far, the representative feature index characterizes the degree of representativeness of the gray-scale extension path of the pixel point in the area to be enhanced for the gray-scale feature area, facilitating the subsequent screening of pixel points with high representativeness and weighting the similarity and relevance between pixel points.

[0088] Step S302: According to the representative feature indices of every two pixel points in the area to be enhanced, adjust the extension similarity degree between every two pixel points to obtain the comprehensive similarity degree between every two pixel points in the area to be enhanced.

[0089] Specifically, taking any two different pixel points in the area to be enhanced as an example, the product of the representative feature index of the first pixel point, the representative feature index of the second pixel point, and the degree of extended similarity between the first pixel point and the second pixel point is used as the comprehensive similarity degree between the first pixel point and the second pixel point.

[0090] More specifically, the comprehensive similarity degree can be expressed by the formula: , represents the comprehensive similarity degree between the first pixel point and the second pixel point, represents the representative feature index of the first pixel point, represents the representative feature index of the second pixel point, represents the degree of extended similarity between the first pixel point and the second pixel point, x represents the x-th pixel point in the area to be enhanced, y represents the y-th pixel point in the area to be enhanced, and .

[0091] It can be understood that the comprehensive similarity degree not only considers the feature similarity and relevance between two pixel points, but also considers the degree of feature representativeness of the pixel points themselves, making the gray-scale features of the pixel points more representative when performing gray-scale enhancement based on similarity later.

[0092] Step S400: Adjust the gray-scale value of each pixel point in the area to be enhanced according to the comprehensive similarity degree between each pixel point and other pixel points in the area to be enhanced, and obtain the enhanced image of the lung CT.

[0093] The greater the similarity between each pixel point and other pixel points in the area to be enhanced, and at the same time the greater the corresponding feature representativeness of the two pixel points, it indicates that the corresponding gray-scale extension paths of the two belong to more common extension features, and further indicates that it is more likely to be more detailed parts such as capillaries, that is, it is more necessary to adjust the gray-scale values of these pixel points.

[0094] Specifically, take any pixel point in the area to be enhanced as the target pixel point, take the pixel points in the area to be enhanced except the target pixel point as the reference pixel points, arrange the reference pixel points in descending order according to the comprehensive similarity degree between the target pixel point and each reference pixel point, and obtain a preset number of reference pixel points as the control pixel points of the target pixel point according to the arrangement order.

[0095] In this embodiment, the preset quantity is set to 20. In other embodiments, the implementer can set it according to the specific implementation scenario. More specifically, the reference pixel points represent some pixel points with the highest similarity in the gray-scale extension direction distribution characteristics in the area to be enhanced. By using the gray-scale values of these pixel points to copy the target pixel points, some representative gray-scale information can be effectively integrated, so that the adjusted gray-scale value can better represent the detailed information.

[0096] Further, using the comprehensive similarity degree between the target pixel point and each reference pixel point, the gray-scale values of each reference pixel point are weighted and averaged to obtain the enhanced gray-scale value of the target pixel point. In this embodiment, taking the nth pixel point in the area to be enhanced as the target pixel point, the enhanced gray-scale value of the target pixel point can be expressed by the formula: , where represents the enhanced gray-scale value of the target pixel point, and n represents the nth pixel point in the area to be enhanced; represents the total number of reference pixel points of the target pixel point, represents the comprehensive similarity degree between the target pixel point and the kth reference pixel point, represents the gray-scale value of the target pixel point and the kth reference pixel point.

[0097] It should be noted that when the value of the enhanced gray-scale value is not an integer, a ceiling operation needs to be performed. This method is a well-known technology and will not be introduced in detail here. Finally, the enhanced gray-scale values of each pixel point in the area to be enhanced are obtained by the same method. Furthermore, the enhanced gray-scale values of each pixel point in the area to be enhanced constitute the enhanced image of the lung CT. The enhanced lung CT image can show relatively clear blood vessel details, and the image enhancement effect is better.

[0098] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A lung CT image enhancement method, characterized in that: The method comprises the following steps: Acquire lung CT images, and perform segmentation preprocessing on the lung CT images to obtain lung target areas and areas to be enhanced; According to the grayscale distribution of each pixel in the area to be enhanced within the neighborhood and the pixel distribution in the lung target area, the correlation of the grayscale extension trend between the pixels in the area to be enhanced is analyzed to obtain the extension similarity between every two pixels in the area to be enhanced, including: According to the grayscale distribution of each pixel in the area to be enhanced within the neighborhood and the pixel distribution in the lung target area, regional growth is performed on each pixel in the area to be enhanced to obtain the grayscale feature area of ​​each pixel in the area to be enhanced; according to the path distribution from the corresponding grayscale feature area to the lung target area of ​​each pixel in the area to be enhanced, the grayscale extension path of each pixel in the area to be enhanced is obtained; according to the grayscale distribution difference of the pixels on the grayscale extension path of every two pixels in the area to be enhanced, the chain code information difference of the pixels and the length difference of the grayscale extension path, the extension similarity between every two pixels in the area to be enhanced is obtained; According to the distribution of pixels in the gray extension direction of each pixel in the area to be enhanced and the position distribution between other pixels and the corresponding gray extension direction, combined with the extension similarity, the comprehensive similarity between every two pixels in the area to be enhanced is obtained, including: According to the number distribution of other pixels outside the gray extension path of each pixel in the area to be enhanced, and the fluctuation of the distance between other pixels and the gray extension path, combined with the length distribution of the gray extension path, the representative feature index of each pixel in the area to be enhanced is obtained; according to the representative feature index of every two pixels in the area to be enhanced, the extension similarity between every two pixels is adjusted to obtain the comprehensive similarity between every two pixels in the area to be enhanced; According to the comprehensive similarity between each pixel and other pixels in the area to be enhanced, the gray value of the pixel is adjusted to obtain an enhanced image of the lung CT.

2. A lung CT image enhancement method according to claim 1, characterized in that: The method for obtaining the grayscale feature area is specifically as follows: Each pixel point in the area to be enhanced is used as an initial seed point, and region growing is performed according to a set region growing rule to obtain a grayscale feature region corresponding to each pixel point in the area to be enhanced; Among them, the regional growing rule is: if the difference between the grayscale values ​​of the initial seed point and the pixels in its neighborhood is less than or equal to the preset difference threshold, the pixel point corresponding to the minimum grayscale value in the neighborhood of the initial seed point is used as a new seed point for growth until there is a pixel point in the lung target area within the neighborhood of the growing seed point, or the difference between the grayscale values ​​of the growing seed point and the pixels in its neighborhood is greater than the difference threshold, then the growth is stopped.

3. A lung CT image enhancement method according to claim 1, characterized in that: The step of obtaining the gray extension path of each pixel point in the area to be enhanced according to the path distribution from the corresponding gray feature area to the lung target area of ​​each pixel point in the area to be enhanced specifically includes: Any pixel point in the area to be enhanced is taken as the selected pixel point, and the pixel point with the shortest distance to the lung target area in the grayscale feature area of ​​the selected pixel point is obtained as the feature pixel point. In the grayscale feature area of ​​the selected pixel point, the shortest path between the selected pixel point and the corresponding feature pixel point is taken as the grayscale extension path of the selected pixel point.

4. A lung CT image enhancement method according to claim 3, characterized in that: The method of obtaining the extension similarity between every two pixels in the area to be enhanced according to the grayscale distribution difference of the pixels on the grayscale extension path of every two pixels in the area to be enhanced, the chain code information difference of the pixels, and the length difference of the grayscale extension path specifically includes: Obtain an 8-chain code sequence of the gray extension path of each pixel in the area to be enhanced; record any two different pixels in the area to be enhanced as the first pixel and the second pixel respectively; Determine a grayscale difference factor based on a difference between grayscale value means of all pixels on a grayscale extension path of a first pixel and a second pixel; Determine a chain code difference factor based on a difference between the means of all chain code values ​​in the 8-chain code sequence corresponding to the first pixel and the second pixel; Determining a path difference factor based on a length difference between grayscale extension paths of the first pixel and the second pixel; A negative correlation process is performed on the product of the grayscale difference factor, the chain code difference factor and the path difference factor to obtain the extension similarity between the first pixel point and the second pixel point.

5. A lung CT image enhancement method according to claim 4, characterized in that: The method for obtaining the representative feature index of each pixel in the area to be enhanced is specifically as follows: In the grayscale feature area of ​​the selected pixel, the variance of the shortest distance between all other pixel points except the grayscale extension path of the selected pixel point and the grayscale extension path is calculated to obtain a first coefficient; In the grayscale feature area of ​​the selected pixel, the number of all other pixel points except the grayscale extension path of the selected pixel point is obtained to obtain a second coefficient; A representative characteristic index of the selected pixel point is obtained according to the first coefficient, the second coefficient and the length of the grayscale extension path of the selected pixel point, the length of the grayscale extension path is positively correlated with the representative characteristic index, and the first coefficient and the second coefficient are both negatively correlated with the representative characteristic index.

6. A lung CT image enhancement method according to claim 5, characterized in that: The step of adjusting the extended similarity between every two pixels in the region to be enhanced according to the representative characteristic index of every two pixels in the region to be enhanced to obtain the comprehensive similarity between every two pixels in the region to be enhanced specifically includes: The product of the representative feature index of the first pixel, the representative feature index of the second pixel, and the extended similarity between the first pixel and the second pixel is taken as the comprehensive similarity between the first pixel and the second pixel.

7. The lung CT image enhancement method according to claim 1, characterized in that: The gray value of each pixel is adjusted according to the comprehensive similarity between each pixel and other pixels in the area to be enhanced to obtain an enhanced image of the lung CT, specifically including: Taking any pixel point in the area to be enhanced as the target pixel point, taking the pixels other than the target pixel point in the area to be enhanced as reference pixels, arranging the reference pixels in descending order of the comprehensive similarity between the target pixel point and each reference pixel point, and obtaining a preset number of reference pixels in the arrangement order as reference pixels of the target pixel point; Using the comprehensive similarity between the target pixel and each reference pixel, the grayscale value of each reference pixel is weighted and averaged to obtain the enhanced grayscale value of the target pixel; The enhanced gray value of each pixel in the area to be enhanced constitutes the enhanced image of the lung CT.

8. The lung CT image enhancement method according to claim 1, characterized in that: The preprocessing of the lung CT image by segmentation to obtain the lung target area and the area to be enhanced specifically includes: The maximum inter-class variance method is used to segment the lung CT images. The area with a gray value greater than the segmentation threshold is taken as the lung target area, and the area with a gray value less than or equal to the segmentation threshold is taken as the area to be enhanced.

Images