Medical image processing method, system, computer device and storage medium

Abstract

The present invention relates to the field of image data analysis technology, specifically to a medical image processing method, system, computer device and storage medium. A medical image processing method comprises the following steps: collecting CT scan data, analyzing the brightness and grayscale around each pixel, establishing a brightness distribution map of each pixel, measuring the average brightness and variation range of the surrounding area, and obtaining image pixel brightness characteristic data. The beneficial effect of the present invention is that the diagnostic accuracy and visual quality of CT images are improved by controlling brightness adjustment, curvature analysis, and texture and contrast optimization. Through brightness adjustment and calculation of curvature and shape index, key edges and curves in the image can be more accurately identified. By iteratively processing the brightness and contrast of the optimized area, as well as refining the texture and detail level, the artifacts and blurred areas in the image can be significantly improved, providing clearer and more reliable images for medical professionals to evaluate and diagnose.

Description

Technical Field

[0001] The present invention relates to the technical field of image data analysis, and in particular to a medical image processing method, system, computer equipment and storage medium. Background Art

[0002] The field of image data analysis technology usually uses algorithms and computing technologies to extract useful information from images, understand and interpret image data. In the medical field, image data analysis technology is used to process and analyze images obtained from various medical imaging devices (such as X-rays, CT scans, MRIs, and ultrasound images) in order to diagnose diseases, monitor treatment effects, and conduct medical research. This enables more accurate identification of lesion location, size, and shape, improving the accuracy of diagnosis and the targeting of treatment.

[0003] Medical image processing methods refer to the application of image data analysis technology to medical image processing to optimize the diagnosis, treatment and research process. The methods support the decision-making of medical professionals by enhancing image quality, automatically identifying disease markers, and extracting clinically relevant feature data. Including but not limited to improving the visualization quality of images, assisting in pathology detection and diagnosis, and conducting patient monitoring and follow-up treatment evaluation. By using these advanced image processing technologies, diseases can be detected earlier, treatment effects can be improved, and patient treatment outcomes and health recovery can be improved.

[0004] Although existing medical image processing technologies can support basic image quality optimization and disease marker identification, they lack sufficient flexibility and accuracy when processing high-complexity and low-contrast medical images. For example, when processing areas with many similar grayscale values, traditional technologies may not be able to effectively distinguish details, resulting in the omission of key diagnostic information. In addition, when processing areas with many similar grayscale values, existing technologies may not be able to effectively distinguish details due to insufficient local analysis capabilities, resulting in the omission of key diagnostic information. This can lead to delayed diagnosis or misdiagnosis, affecting treatment outcomes. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a medical image processing method, system, computer device and storage medium.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a medical image processing method, comprising the following steps:

[0007] S1: Collect CT scan data, analyze the brightness and grayscale around each pixel, establish a brightness distribution map for each pixel, measure the average brightness and variation range of the surrounding area, and obtain image pixel brightness characteristic data;

[0008] S2: Based on the image pixel brightness characteristic data, refer to the brightness average and change of adjacent pixels, adjust the brightness of each pixel in the CT image to generate an adjusted brightness map;

[0009] S3: Analyzing the local curvature and shape index of the CT image from the adjusted brightness image, identifying key edges and curves in the CT image, and obtaining a geometric feature map;

[0010] S4: by analyzing the shape and curvature information in the geometric feature map, selecting the area that needs to be iteratively processed according to the curvature size, performing brightness and contrast optimization operations, and generating an artifact correction map;

[0011] S5: Refining the texture and detail levels in the artifact correction image, optimizing feature recognition by adjusting the texture brightness of the local area, and generating an edge-optimized image.

[0012] As a further solution of the present invention, the image pixel brightness characteristic data includes pixel brightness values, adjacent pixel brightness variances and brightness gradients; the adjusted brightness map includes smoothed regional brightness, correction results of local brightness anomalies and the state of overall brightness balance; the geometric feature map includes curvature points in the image, tracking marks of key curves and edge intensity mapping; the artifact correction map includes optimized contrast areas, brightness areas and edge clarity processing; the edge-optimized image includes refined texture areas, adjusted local visual contrast and optimized color depth.

[0013] As a further solution of the present invention, the specific steps of collecting CT scan data, analyzing the brightness and grayscale around each pixel, establishing a brightness distribution map of each pixel, measuring the average brightness and variation range of the surrounding area, and obtaining image pixel brightness characteristic data are as follows:

[0014] S101: Collect CT scan data, record the brightness and grayscale value of each pixel, and obtain original pixel data;

[0015] S102: Based on the original pixel data, calculate the average brightness and grayscale fluctuation around each pixel to obtain a local brightness distribution map;

[0016] S103: extracting the overall average brightness and the variation range from the local brightness distribution map to form image pixel brightness characteristic data.

[0017] As a further solution of the present invention, based on the image pixel brightness characteristic data, referring to the brightness average and change of adjacent pixels, the brightness of each pixel in the CT image is adjusted, and the specific steps of generating the adjusted brightness map are as follows:

[0018] S201: Obtaining brightness information of each pixel and its surrounding pixels from the image pixel brightness characteristic data, evaluating brightness differences, and generating a pixel brightness adjustment value list according to the brightness value that needs to be adjusted for each pixel point;

[0019] S202: Using the pixel brightness adjustment value list, adjusting the brightness of each pixel, including increasing or decreasing the brightness, balancing the brightness differences in the image area, and generating a brightness adjustment intermediate image;

[0020] S203: Apply the adjustment of all pixels in the brightness adjustment intermediate image to the original CT image to generate an adjusted brightness image.

[0021] As a further solution of the present invention, the specific steps of analyzing the local curvature and shape index of the CT image from the adjusted brightness image, identifying the key edges and curves in the CT image, and obtaining the geometric feature map are as follows:

[0022] S301: extracting the local curvature of each pixel based on the adjusted brightness map, and generating local curvature data by analyzing the curvature change of each area;

[0023] S302: using the local curvature data, calculating the shape index through differential geometry method, identifying key edges and curves in the image, and generating a key shape analysis diagram;

[0024] S303: Integrate the data in the key shape analysis graph, identify key edges and curves in the image, and generate a geometric feature graph.

[0025] As a further solution of the present invention, the differential geometry method adopts the formula:

[0026] Calculate shape indices to identify key edges and curves in images;

[0027] in, is the shape index, used for each pixel , is the local curvature, indicating the The curvature size at the pixel point, is the adjustment coefficient used to balance the local pixel intensity variation Contribution to the shape index, is the standard deviation of local pixel intensity, is the derivative of curvature with respect to arc length, which indicates the rate at which curvature changes with the arc length of the image. is the adjustment coefficient used to balance the local average grayscale difference The effect on the shape index, is the difference between the local average grayscale and the global average grayscale.

[0028] As a further solution of the present invention, by analyzing the shape and curvature information in the geometric feature map, selecting the area that needs to be iteratively processed according to the curvature size, performing brightness and contrast optimization operations, and generating the artifact correction map in the following specific steps:

[0029] S401: According to the curvature in the geometric feature map, identify the area where the curvature changes significantly, the area corresponds to the artifact or feature change in the image, and obtain the target processing area;

[0030] S402: performing brightness adjustment and contrast optimization on the target processing area, iteratively adjusting local area parameters, and generating a local optimized brightness map;

[0031] S403: Integrate all adjustment parameters in the local optimized brightness map, apply it to the entire CT image again, and generate an artifact correction map.

[0032] As a further solution of the present invention, the specific steps of refining the texture and detail level in the artifact correction image, optimizing feature recognition by adjusting the texture brightness of the local area, and generating an edge-optimized image are as follows:

[0033] S501: Analyze the texture details of each area based on the artifact correction map, perform texture enhancement on the area with unclear texture, and generate a texture optimization map;

[0034] S502: Selecting a key area from the texture optimization map, adjusting the light and dark contrast of the texture area, and generating an iteratively adjusted texture map;

[0035] S503: Applying the iteratively adjusted texture map to the artifact correction map to unify the texture and detail level of the key area and generate an edge-optimized image.

[0036] A medical image processing system is used to execute a medical image processing method, and the medical image processing system comprises:

[0037] The brightness characteristic analysis module collects CT scan data, records the brightness and grayscale values ​​of each pixel, calculates the average brightness and grayscale fluctuation around each pixel, obtains the local brightness distribution map, extracts the overall average brightness and variation range from the local brightness distribution map, and forms the image pixel brightness characteristic data;

[0038] The brightness adjustment module adjusts the brightness of each pixel in the CT image based on the image pixel brightness characteristic data to obtain an adjusted brightness map, analyzes the local curvature and shape index in the adjusted brightness map, performs brightness and contrast optimization operations, and generates an artifact correction map;

[0039] The geometric feature analysis module extracts the local curvature of each pixel based on the artifact correction map, calculates the shape index through the differential geometry method, identifies the key edges and curves in the image, and generates a geometric feature map;

[0040] Based on the geometric feature map, the detail optimization module analyzes the texture details of each area, performs texture enhancement operations, adjusts the light and dark contrast of the texture area, unifies the texture and detail levels of the key area, and generates an edge-optimized image.

[0041] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements a medical image processing system as described above when executing the computer program.

[0042] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a medical image processing method as described above.

[0043] Compared with the prior art, the advantages and positive effects of the present invention are:

[0044] In the present invention, the diagnostic accuracy and visual quality of CT images are improved by controlling brightness adjustment, curvature analysis, and texture and contrast optimization. Through brightness adjustment and calculation of curvature and shape index, key edges and curves in the image can be more accurately identified, and through iterative processing to optimize the brightness and contrast of the area, as well as refine the texture and detail level, artifacts and blurred areas in the image can be significantly improved, providing clearer and more reliable images for medical professionals to evaluate and diagnose. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0046] Figure 2 This is a detailed flow chart of S1 of the present invention;

[0047] Figure 3 This is a detailed flow chart of S2 of the present invention;

[0048] Figure 4 This is a detailed flow chart of S3 of the present invention;

[0049] Figure 5 This is a detailed flow chart of S4 of the present invention;

[0050] Figure 6 This is a detailed flow chart of S5 of the present invention;

[0051] Figure 7 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0053] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0054] See also Figure 1 The present invention provides a technical solution: a medical image processing method, comprising the following steps:

[0055] S1: Collect CT scan data, analyze the brightness and grayscale around each pixel, establish a brightness distribution map for each pixel, measure the average brightness and variation range of the surrounding area, and obtain image pixel brightness characteristic data;

[0056] S2: Based on the image pixel brightness characteristic data, refer to the brightness average and change of adjacent pixels, adjust the brightness of each pixel in the CT image to generate an adjusted brightness map;

[0057] S3: Analyze the local curvature and shape index of the CT image from the adjusted brightness image, identify key edges and curves in the CT image, and obtain a geometric feature map;

[0058] S4: By analyzing the shape and curvature information in the geometric feature map, the area that needs to be iteratively processed is selected according to the curvature size, and the brightness and contrast optimization operation is performed to generate an artifact correction map;

[0059] S5: Refine the texture and detail levels in the artifact correction image, optimize feature recognition by adjusting the texture brightness in the local area, and generate an edge-optimized image.

[0060] The image pixel brightness characteristic data includes pixel brightness value, adjacent pixel brightness variance and brightness gradient. The adjusted brightness map includes the smoothed regional brightness, the correction results of local brightness anomalies and the overall brightness balance status. The geometric feature map includes the curvature points in the image, the tracking marks of key curves and the edge intensity mapping. The artifact correction map includes the optimized contrast area, brightness area and edge clarity. The edge optimized image includes the refined texture area, the adjusted local visual contrast and the optimized color depth.

[0061] See also Figure 2 , collect CT scan data, analyze the brightness and grayscale around each pixel, establish a brightness distribution map for each pixel, measure the average brightness and variation range of the surrounding area, and obtain the image pixel brightness characteristic data. The specific steps are as follows:

[0062] S101: The process of collecting CT scan data, recording the brightness and grayscale value of each pixel, and obtaining the original pixel data is as follows;

[0063] Acquiring CT scan data In this step, the patient's scan image is acquired through the CT scanning device, and the brightness of each pixel in the image is recorded. and Grayscale Values. These values ​​are stored in the original pixel data in the form of a two-dimensional matrix. At the same time, the scanned resolution and image size information are recorded to provide basic data for subsequent image processing.

[0064] S102: Based on the original pixel data, the average brightness and grayscale fluctuation around each pixel are calculated to obtain a local brightness distribution map as follows;

[0065] By calculating the local brightness distribution for each pixel in the image , calculate its surrounding The average brightness of the pixels Grayscale Fluctuation , and get the local brightness distribution map. The calculation formula for average brightness is: ,in Indicates The brightness values ​​of the surrounding pixels, represents the number of neighboring pixels considered, is the index of the surrounding pixels. The grayscale fluctuation is obtained by calculating the standard deviation, and the formula is: ,in, It is The grayscale values ​​of the surrounding pixels, is the average grayscale of these neighboring pixels.

[0066] S103: The process of extracting the overall average brightness and variation range from the local brightness distribution map to form image pixel brightness characteristic data is as follows;

[0067] Extract the overall average brightness from the local brightness distribution map and range of variation The overall average brightness is calculated as: ,in, It is The average brightness of the pixels, is the total number of pixels in the image. , which is the difference between the maximum and minimum average brightness, and the calculation formula is , provides an indicator to measure the uniformity of the overall brightness distribution of the image.

[0068] See also Figure 3 Based on the image pixel brightness characteristic data, the brightness of each pixel in the CT image is adjusted with reference to the brightness average and change of adjacent pixels. The specific steps for generating the adjusted brightness map are as follows:

[0069] S201: The process of obtaining brightness information of each pixel and its surrounding pixels from the image pixel brightness characteristic data, evaluating the brightness difference, and generating a pixel brightness adjustment value list according to the brightness value that needs to be adjusted for each pixel point is as follows;

[0070] The brightness characteristic data of each pixel in the image is used to extract the brightness information of each pixel and its surrounding pixels. The brightness difference with its surrounding pixels, using the difference value Indicates that the calculation formula is: ,in, It is The brightness of a pixel, is the average brightness of the surrounding pixels. Based on the calculated brightness difference, determine the brightness value that needs to be adjusted for each pixel. These brightness adjustment values ​​are compiled into a list , each element Represents the adjustment amount of the corresponding pixel, the formula is: ,in, is the adjustment coefficient, which is used to control the adjustment range.

[0071] S202: Using the pixel brightness adjustment value list, adjusting the brightness of each pixel, including increasing or decreasing the brightness, balancing the brightness difference of the image area, and generating a brightness adjustment intermediate image as follows;

[0072] Using the generated list of pixel brightness adjustment values, adjust the brightness of each pixel. The specific operation is to increase or decrease the brightness of each pixel according to the value in the list to balance the brightness differences in the image. The new brightness value of each pixel The calculation formula is: ,in, is the brightness value of the original pixel, is the adjustment value of the pixel in the adjustment list. After adjustment in this way, a brightness adjustment intermediate image is generated, which shows the effect of all pixel brightness adjustments.

[0073] S203: Apply the adjustment of all pixels in the brightness adjustment intermediate image to the original CT image to generate an adjusted brightness image as follows;

[0074] Apply these adjustments to the original CT image. The final brightness of each pixel needs to be between 0 and 255 according to the adjustment value to maintain the integrity of the image data and the quality of visualization. The brightness of each pixel after adjustment is calculated as follows: ,in, is to adjust the pixel brightness value of the middle image, and is based on The correction amount calculated by the value of . Less than 0, then is set to , to increase the brightness to 0; if If it exceeds 255, is set to , to reduce the brightness to 255; if is already in the range of 0 to 255, then If it is 0, no further adjustment is required.

[0075] See also Figure 4 ,From the adjusted brightness map, analyze the local curvature and shape index of the CT image, identify the key edges and curves in the CT image, and obtain the geometric feature map in the following specific steps:

[0076] S301: Based on the adjusted brightness map, extract the local curvature of each pixel point, and generate the local curvature data by analyzing the curvature change of each area. The process is as follows;

[0077] Extract the local curvature of each pixel Based on the adjusted brightness map, each pixel The local passing curvature Calculate and evaluate the curvature change of each area in the image. The calculation of local curvature is achieved by using the second-order derivative and the difference method. The specific formula is: ,in, and Represents the adjusted pixel brightness Second-order derivatives in the x and y directions. These derivatives are calculated by the brightness difference between pixels and are used to evaluate the local curvature change of each pixel in the image, thereby generating data representing the local curvature of each region.

[0078] S302: Using local curvature data, through differential geometry methods, calculating shape indexes, identifying key edges and curves in the image, and generating key shape analysis diagrams are as follows;

[0079] Calculate shape index and generate key shape analysis diagrams Using local curvature data, the shape index is further calculated using differential geometry methods The shape index is determined by the following formula, taking into account the local curvature and its rate of change.

[0080] Differential geometry method, using the formula:

[0081] Calculate shape indices to identify key edges and curves in images;

[0082] in, is the improved shape index for each pixel , helping to more accurately identify key edges and curves in images, especially in areas with complex structures, is the local curvature, indicating the The curvature size at each pixel is used to identify curves and edges in the image. is the adjustment coefficient used to balance the local pixel intensity variation Contribution to the shape index, ensuring that texture characteristics are properly reflected in the calculations, is the standard deviation of local pixel intensity, calculated as the average difference in pixel brightness in the local area, and is used to measure the consistency of pixel brightness. Increasing this parameter helps emphasize areas with large texture differences. It is the derivative of curvature with respect to arc length, which indicates the rate at which curvature changes with the arc length of the image. It is key to determining the speed of change of curves or edges. Is the adjustment coefficient, used to balance the local average grayscale difference The effect on the shape index makes brightness contrast play a role in shape recognition. It is the difference between the local average grayscale and the global average grayscale, which is used to evaluate the brightness contrast between the area and the whole, which helps to identify edges that may be formed due to brightness changes.

[0083] The calculation process is as follows;

[0084] Assume that the image is processed into a gray value matrix, each pixel There is a gray value . Local curvature This can be approximated by applying the second-order partial derivative to this grayscale value:

[0085] and Respectively represent the images in and Curvature in direction.

[0086] Calculate the arc-length derivative of curvature Arc-length derivative of curvature Represents how the curvature varies along the graph curve:

[0087]

[0088] is the distance between adjacent pixels, which can usually be assumed to be unit length.

[0089] Calculate local pixel intensity variation Local pixel intensity variation :

[0090] It is The grayscale values ​​of neighboring pixels, is the average gray value of these neighboring pixels, is the total number of neighboring pixels considered.

[0091] Calculate the local and global average grayscale difference Local and global average grayscale difference :

[0092]

[0093] is the average gray value of the local area around the target pixel, is the average gray value of the entire image.

[0094] Improved shape index The formula is as follows: In the formula, each component has a clear source and calculation method, ensuring accuracy and repeatability.

[0095] Improved shape index formula It can more effectively highlight and identify key edges and curves in CT images, especially in complex anatomical areas.

[0096] S303: The process of integrating the data in the key shape analysis graph, identifying the key edges and curves in the image, and generating a geometric feature graph is as follows;

[0097] A continuous weighting function is used to process the shape index so that the shape index is above a certain threshold. The area is highlighted, defining the weight function , based on the relationship between the shape index and the threshold, the weight of each pixel is calculated as follows: This function is a standard sigmoid function that is used to smoothly transition the shape index value without hard threshold cutoff. Here, is the base of the natural logarithm, ensuring that when the shape exponent Approaching or exceeding the threshold hour, is approaching 1 quickly, and when Much lower than hour, Close to 0.

[0098] See also Figure 5 , by analyzing the shape and curvature information in the geometric feature map, according to the curvature size, the area that needs to be iteratively processed is selected, and the brightness and contrast optimization operations are performed. The specific steps to generate the artifact correction map are as follows:

[0099] S401: According to the curvature in the geometric feature map, the region where the curvature changes significantly is identified, and the region corresponds to the artifact or feature change in the image. The process of obtaining the target processing region is as follows;

[0100] Using geometric feature maps, analyze the local curvature of each pixel By calculating the gradient of the curvature , we can identify areas where the curvature changes significantly, which usually corresponds to artifacts or feature changes in the image. The calculation formula is: This step is to identify the gradient value exceeding the set threshold These areas are marked as areas that require special treatment so that more detailed brightness and contrast adjustments can be made in subsequent steps.

[0101] S402: The process of adjusting brightness and optimizing contrast of the target processing area, iteratively adjusting local area parameters, and generating a local optimized brightness map is as follows;

[0102] Brightness adjustment and contrast optimization are performed on pixels in each region. Brightness adjustment uses a linear transformation to adjust the brightness , and contrast adjustment is implemented through a nonlinear transformation to enhance the visual effect of the local image. The brightness adjustment formula is as follows: , contrast optimization uses the following formula: ,in, and represent the overall average brightness and the local average brightness respectively, and is the adjustment coefficient, which is used to control the degree of brightness and contrast adjustment. This method allows the image features of each processed area to be gradually refined, making the local image clearer and more accurate.

[0103] S403: The process of integrating all adjustment parameters in the local optimized brightness map and applying it to the entire CT image again to generate an artifact correction map is as follows;

[0104] To ensure that all local adjustments are integrated into the original CT image, a composite image with no artifacts and optimized brightness and contrast is produced. The integration process uses the formula: ,in, is the adjusted brightness value, is the brightness value of the original image, and is a weight factor that balances the contributions of the original and adjusted images. In this way, the generated artifact correction map reflects both accurate local adjustments and maintains the overall characteristics of the original image.

[0105] See also Figure 6 , refine the texture and detail level in the artifact correction image, optimize the feature recognition by adjusting the texture brightness of the local area, and generate the edge-optimized image. The specific steps are as follows:

[0106] S501: Based on the artifact correction map, the texture details of each area are analyzed, and the texture is enhanced for the area with unclear texture. The process of generating the texture optimization map is as follows;

[0107] Analyze the texture details of each area. Evaluate the texture prominence of each area by calculating the local variance of texture intensity. Calculate the Texture variance The formula is: ,in, Indicates The texture value of each pixel, is the average pixel texture value in the area, Represents the number of pixels in the local area under consideration. For areas with unclear texture, that is In the lower area, texture enhancement is performed. Texture enhancement is achieved by adjusting the texture intensity of each pixel. The enhancement formula is: , is an adjustment coefficient that controls the magnitude of texture enhancement. In this way, the area with unclear texture is enhanced and a texture optimized map is generated.

[0108] S502: Select key areas from the texture optimization map, adjust the light and dark contrast of the texture area, and generate an iteratively adjusted texture map as follows;

[0109] From the texture optimization map, key areas are selected for further processing. These key areas are defined by areas where the texture contrast is significantly higher than the surrounding area. In these selected areas, the light and dark contrast of the texture area is adjusted to make the texture details stand out more. The texture light and dark adjustment is implemented by the following formula: ,in, is the contrast adjustment factor, is the average value of the adjusted texture value. Through this adjustment, an iteratively adjusted texture map is generated, in which the texture details in the key areas are further optimized and strengthened.

[0110] S503: The process of applying the iteratively adjusted texture map to the artifact correction map to unify the texture and detail level of the key area and generate an edge-optimized image is as follows;

[0111] The iteratively adjusted texture map is applied back to the artifact correction map to unify the texture and detail level of key areas. This process integrates the texture details of the two images through linear interpolation, as follows: , is the pixel value in the final generated image, is the texture value in the iteratively adjusted texture map, is the original pixel value in the artifact-corrected image, and is a weight factor used to balance the contribution of the texture map and the original image. After this processing, the key areas in the image are significantly optimized in terms of texture and detail level, generating an edge-optimized image.

[0112] See also Figure 7 , a medical image processing system is used to perform a medical image processing method, and a medical image processing system comprises:

[0113] The brightness characteristic analysis module collects CT scan data, records the brightness and grayscale values ​​of each pixel, calculates the average brightness and grayscale fluctuation around each pixel, obtains the local brightness distribution map, extracts the overall average brightness and variation range from the local brightness distribution map, and forms the image pixel brightness characteristic data;

[0114] The brightness adjustment module adjusts the brightness of each pixel in the CT image based on the image pixel brightness characteristic data to obtain an adjusted brightness map, analyzes the local curvature and shape index in the adjusted brightness map, performs brightness and contrast optimization operations, and generates an artifact correction map;

[0115] The geometric feature analysis module extracts the local curvature of each pixel based on the artifact correction map, calculates the shape index through differential geometry methods, identifies key edges and curves in the image, and generates a geometric feature map;

[0116] The detail optimization module analyzes the texture details of each area based on the geometric feature map, performs texture enhancement operations, adjusts the light and dark contrast of the texture area, unifies the texture and detail levels of the key areas, and generates an edge-optimized image.

[0117] A computer device comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, a medical image processing system as described above is implemented.

[0118] A computer-readable storage medium stores a computer program, which implements the steps of the above-mentioned medical image processing method when executed by a processor.

[0119] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A medical image processing method, It is characterized in that The following steps are involved: Collect CT scan data, analyze the brightness and grayscale around each pixel, establish a brightness distribution map for each pixel, measure the average brightness and variation range of the surrounding area, and obtain image pixel brightness characteristic data; Based on the image pixel brightness characteristic data, referring to the brightness average and change of adjacent pixels, adjusting the brightness of each pixel in the CT image to generate an adjusted brightness map; Analyzing the local curvature and shape index of the CT image from the adjusted brightness image, identifying key edges and curves in the CT image, and obtaining a geometric feature map; By analyzing the shape and curvature information in the geometric feature map, according to the curvature size, the area that needs to be iteratively processed is selected, and brightness and contrast optimization operations are performed to generate an artifact correction map; Refining the texture and detail levels in the artifact correction image, optimizing feature recognition by adjusting the texture brightness of the local area, and generating an edge-optimized image; The image pixel brightness characteristic data includes pixel brightness value, adjacent pixel brightness variance and brightness gradient; the adjusted brightness map includes smoothed regional brightness, correction results of local brightness anomalies and overall brightness balance; the geometric feature map includes curvature points in the image, tracking marks of key curves and edge intensity mapping; the artifact correction map includes optimized contrast areas, brightness areas and edge clarity processing; the edge-optimized image includes refined texture areas, adjusted local visual contrast and optimized color depth; The specific steps of analyzing the local curvature and shape index of the CT image from the adjusted brightness image, identifying the key edges and curves in the CT image, and obtaining the geometric feature map are as follows: Based on the adjusted brightness map, extract the local curvature of each pixel, and generate local curvature data by analyzing the curvature change of each area; Using the local curvature data, a shape index is calculated through a differential geometry method, key edges and curves in the image are identified, and a key shape analysis diagram is generated; Integrate the data in the key shape analysis graph, identify key edges and curves in the image, and generate a geometric feature graph; The differential geometry method uses the formula: Calculate shape indices to identify key edges and curves in images; in, is the shape index, used for each pixel , is the local curvature, indicating the The curvature size at the pixel point, is the adjustment coefficient used to balance the local pixel intensity variation Contribution to the shape index, is the standard deviation of local pixel intensity, is the derivative of curvature with respect to arc length, which indicates the rate at which curvature changes with the arc length of the image. is the adjustment coefficient used to balance the local average grayscale difference The effect on the shape index, is the difference between the local average grayscale and the global average grayscale; By analyzing the shape and curvature information in the geometric feature map, selecting the area that needs to be iteratively processed according to the curvature size, performing brightness and contrast optimization operations, and generating the artifact correction map in the following specific steps: According to the curvature size in the geometric feature map, the area where the curvature changes significantly is identified, the area corresponds to the artifact or feature change in the image, and the target processing area is obtained; Performing brightness adjustment and contrast optimization on the target processing area, iteratively adjusting local area parameters, and generating a local optimized brightness map; Integrate all adjustment parameters in the local optimized brightness map and apply it to the entire CT image again to generate an artifact correction map; The specific steps of refining the texture and detail level in the artifact correction image, optimizing feature recognition by adjusting the texture brightness of the local area, and generating an edge-optimized image are as follows: Based on the artifact correction map, analyzing the texture details of each area, performing texture enhancement on the area with unclear texture, and generating a texture optimization map; Selecting a key area from the texture optimization map, adjusting the light and dark contrast of the texture area, and generating an iteratively adjusted texture map; The iteratively adjusted texture map is applied to the artifact correction map to unify the texture and detail level of the key area and generate an edge-optimized image.

2. The medical image processing method according to claim 1, It is characterized in that Based on the image pixel brightness characteristic data, referring to the brightness average and change of adjacent pixels, the specific steps of adjusting the brightness of each pixel in the CT image and generating the adjusted brightness map are as follows: Acquire brightness information of each pixel and its surrounding pixels from the image pixel brightness characteristic data, evaluate brightness difference, and generate a pixel brightness adjustment value list according to the brightness value that needs to be adjusted for each pixel point; Using the pixel brightness adjustment value list, adjusting the brightness of each pixel, including increasing or decreasing the brightness, balancing the brightness differences in the image area, and generating a brightness adjustment intermediate image; The adjustment of all pixels in the brightness adjustment intermediate image is applied to the original CT image to generate an adjusted brightness image.

3. A medical image processing system, It is characterized in that The medical image processing system is used to execute the medical image processing method according to any one of claims 1 to 2, and the medical image processing system comprises: The brightness characteristic analysis module collects CT scan data, records the brightness and grayscale values ​​of each pixel, calculates the average brightness and grayscale fluctuation around each pixel, obtains the local brightness distribution map, extracts the overall average brightness and variation range from the local brightness distribution map, and forms the image pixel brightness characteristic data; The brightness adjustment module adjusts the brightness of each pixel in the CT image based on the image pixel brightness characteristic data to obtain an adjusted brightness map, analyzes the local curvature and shape index in the adjusted brightness map, performs brightness and contrast optimization operations, and generates an artifact correction map; The geometric feature analysis module extracts the local curvature of each pixel based on the artifact correction map, calculates the shape index through the differential geometry method, identifies the key edges and curves in the image, and generates a geometric feature map; Based on the geometric feature map, the detail optimization module analyzes the texture details of each area, performs texture enhancement operations, adjusts the light and dark contrast of the texture area, unifies the texture and detail levels of the key area, and generates an edge-optimized image.

4. A computer device comprising a memory and a processor, It is characterized in that The memory stores a computer program, and the processor implements the steps of a medical image processing method according to any one of claims 1 to 2 when executing the computer program.

5. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of a medical image processing method according to any one of claims 1 to 2 are implemented.

Images