A CT image processing method and system for medical injuries

Abstract

The present invention provides a method and system for processing CT images of medical injuries, relating to the field of medical image processing. The method includes: performing data preprocessing on the CT images; determining the noise type of the noise in the CT images; determining the noise intensity of the noise in the CT images; determining a training data set according to the noise type and the noise intensity; training a noise processing model according to the training data set to obtain a trained noise processing model; processing the CT images according to the trained noise processing model to obtain denoised CT images; determining the injury area at the injury position in the denoised CT images and determining the second CT value of the pixels at the injury position; determining an injury severity coefficient according to the injury area and the second CT value; and generating an injury report according to the injury severity coefficient. According to the present invention, the accuracy and effectiveness of the detailed analysis of the injury position in the CT images can be improved.

Description

Technical Field

[0001] The present invention relates to the field of medical image processing, and particularly to a method and system for processing CT images of medical injuries. Background Art

[0002] In the related art, CN117237255A discloses a CT image processing method, device, storage medium, and CT machine, belonging to the field of medical image processing, including: obtaining a first-resolution CT image; inputting the first-resolution CT image into a CT image processing model to obtain a second-resolution CT image, where the resolution of the second-resolution CT image is higher than that of the first-resolution CT image; wherein, the CT image processing model is trained using sample CT images and labeled CT images with a resolution higher than that of the sample CT images, and the sample CT images are reconstructed based on projection data; this solution can improve the resolution of CT images.

[0003] CN103971387A discloses a method for CT image reconstruction, including the following steps: obtaining original data according to CT scanning; correcting the original data to obtain corrected data; denoising the corrected data to obtain denoised data; rearranging the denoised data to obtain rearranged data; convolving the rearranged data to obtain convolved data; performing backprojection processing on the convolved data to obtain a full-scan field-of-view image and a clinically selected field-of-view image; obtaining an error image based on the full-scan field-of-view image; obtaining a CT image based on the clinically selected field-of-view image and the error image. The method of this solution obtains an error image through the full-scan field-of-view image and obtains a CT image based on the clinically selected field-of-view image and the error image, which can ensure the resolution of the reconstructed CT image and can greatly reduce the computational amount in the reconstruction process and improve the speed of image reconstruction.

[0004] Based on the above related technologies, the resolution of CT images can be improved. However, the related technologies do not analyze the content in the CT images, that is, the degree of injury of the injured parts in the CT images cannot be analyzed.

[0005] The information disclosed in the background art part of the present application is only intended to deepen the understanding of the general background art of the present application, and should not be regarded as an admission or any form of implication that this information constitutes the prior art known to those skilled in the art. Summary of the Invention

[0006] The present invention provides a method and system for processing CT images of medical injuries, which can solve the technical problem that the related technologies cannot analyze the degree of injury of the injured parts in the CT images.

[0007] According to the first aspect of the present invention, there is provided a method for processing CT images of medical injuries, including:

[0008] Perform data preprocessing on the CT image;

[0009] Determine the noise type of the noise in the CT image;

[0010] Determine the noise intensity of the noise in the CT image;

[0011] According to the noise type and the noise intensity, determine a training data set, wherein the training noise type of the training CT images in the training data set is the same as the noise type;

[0012] According to the training data set, train a noise processing model to obtain a trained noise processing model;

[0013] Process the CT image according to the trained noise processing model to obtain a denoised CT image;

[0014] Determine the damage area at the damage position in the denoised CT image, and determine the second CT value of the pixels at the damage position;

[0015] According to the damage area and the second CT value, determine a damage severity coefficient;

[0016] Generate a damage report according to the damage severity coefficient.

[0017] According to the second aspect of the present invention, there is provided a medical damage CT image processing system, including:

[0018] A preprocessing module for performing data preprocessing on the CT image;

[0019] A noise type module for determining the noise type of the noise in the CT image;

[0020] A noise intensity module for determining the noise intensity of the noise in the CT image;

[0021] A training data module for determining a training data set according to the noise type and the noise intensity, wherein the training noise type of the training CT images in the training data set is the same as the noise type;

[0022] A training model module for training a noise processing model according to the training data set to obtain a trained noise processing model;

[0023] A training model module for processing the CT image according to the trained noise processing model to obtain a denoised CT image;

[0024] An image analysis module for determining the damage area at the damage position in the denoised CT image, and determining the second CT value of the pixels at the damage position;

[0025] An injury degree module, configured to determine an injury severity coefficient according to the injury area and the second CT value;

[0026] An injury report module, configured to generate an injury report according to the injury severity coefficient.

[0027] Technical effects: According to the present invention, the noise type and noise intensity in a medical injury CT image can be accurately analyzed, and a training data set can be determined according to the noise type and noise intensity to train a noise processing model. Further, according to the denoised medical injury CT image, the injury area and CT value of the injury site can be determined. Furthermore, the injury degree at the injury position can be evaluated according to the injury area and CT value, which is beneficial to improving the accuracy and effectiveness of the detailed analysis of the injury position in the CT image. When determining the noise intensity, the noise intensity of the noise in the CT image can be determined according to the CT value of the pixel and the number of pixels, providing a data basis for subsequent determination of the training data set and improving the calculation efficiency. When determining the peak signal-to-noise ratio, the peak signal-to-noise ratio can be determined according to the pixel value and the reference pixel value, improving the convenience of calculation. When determining the training loss function, the influence of the spatial resolution, contrast resolution, and peak signal-to-noise ratio on the noise intensity can be used to determine the influence of the above data on the error of predicting the noise intensity. Based on this influence, as well as the relative error of the predicted noise intensity and the data volume of the training data set, the training loss function is set, so that during the training process of the noise processing model, the training loss function is reduced, and the trained noise processing model is more suitable for the noise reduction processing of the current type and intensity of CT images, and more specifically improves the accuracy of the noise processing model. When determining the injury severity coefficient, the injury severity coefficient is determined according to the second CT value of the first pixel sampling point, the second CT value of the second pixel sampling point, and the injury area. During the calculation process, the overall most severe injury degree of the peripheral area and the central area in the injury position can be determined according to the injury degree at the pixel sampling point in the similar shape. Further, according to the overall injury degree of the peripheral area and the central area in the injury position, the overall injury degree of the injury position is determined, and combined with the injury area, the comprehensive injury severity of the injury position is determined, improving the comprehensiveness and accuracy of the injury severity coefficient.

[0028] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present invention. According to the following detailed description of the exemplary embodiments with reference to the accompanying drawings, other features and aspects of the present invention will be clearer. Description of the Drawings

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other embodiments can be obtained based on these drawings;

[0030] Figure 1 Exemplarily shows a schematic flowchart of a medical injury CT image processing method according to an embodiment of the present invention;

[0031] Figure 2 Exemplarily shows a block diagram of a medical injury CT image processing system according to an embodiment of the present invention. Detailed implementation manners

[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, rather than all, embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0033] The following uses specific embodiments to elaborate on the technical solutions of the present invention in detail. These several specific embodiments can be combined with each other. For the same or similar concepts or processes, they may not be repeated in some embodiments.

[0034] Figure 1 Exemplarily shows a schematic flowchart of a medical injury CT image processing method according to an embodiment of the present invention. The method includes:

[0035] Step S101, perform data preprocessing on the CT image;

[0036] Step S102, determine the noise type of the noise in the CT image;

[0037] Step S103, determine the noise intensity of the noise in the CT image;

[0038] Step S104, according to the noise type and the noise intensity, determine a training data set, wherein the training noise type of the training CT images in the training data set is the same as the noise type;

[0039] Step S105, train a noise processing model according to the training data set to obtain a trained noise processing model;

[0040] Step S106: Process the CT image according to the trained noise processing model to obtain a denoised CT image;

[0041] Step S107: Determine the damaged area at the damaged position in the denoised CT image, and determine the second CT value of the pixels at the damaged position;

[0042] Step S108: Determine the damage severity coefficient according to the damaged area and the second CT value;

[0043] Step S109: Generate a damage report according to the damage severity coefficient.

[0044] According to the medical damage CT image processing method of the embodiment of the present invention, the noise type and noise intensity in the medical damage CT image can be accurately analyzed, and the training data set is determined according to the noise type and noise intensity to train the noise processing model, and according to the denoised medical damage CT image, the damaged area and CT value of the damaged part are determined. Further, the damage degree at the damaged position is evaluated according to the damaged area and CT value, which is beneficial to improving the accuracy and effectiveness of the detailed analysis of the damaged position in the CT image.

[0045] According to an embodiment of the present invention, in step S101, data preprocessing is performed on the CT image.

[0046] For example, preprocessing operations such as normalizing, cropping, and enhancing the CT image are performed.

[0047] According to an embodiment of the present invention, in step S102, the noise type of the noise in the CT image is determined.

[0048] For example, by observing the distribution of the noise in the image, the noise type of the noise in the CT image is determined. Quantum noise usually appears as a randomly distributed granular appearance, while the hardware system noise may appear as a more uniform or more concentrated noise pattern. Therefore, according to the characteristics of quantum noise and hardware system noise, the noise type of the noise in the CT image can be determined.

[0049] According to an embodiment of the present invention, in step S103, the noise intensity of the noise in the CT image is determined.

[0050] According to an embodiment of the present invention, step S103 includes:

[0051] In the CT image, a preset area is determined;

[0052] Obtain the CT value and the number of pixels of each pixel in the preset area;

[0053] According to the CT value of the pixel and the number of pixels, the noise intensity of the noise in the CT image is determined.

[0054] For example, in a CT image, a preset region is selected. The preset region is located in a non-damaged region within the region where the organ is located in the CT image. The preset region should be as large and uniform as possible to accurately reflect the intensity of the noise. By using the automatic calculation and display functions of the CT scanner, the CT values of each pixel within the preset region are obtained. Based on the size and resolution of the preset region, the number of pixels within the preset region is determined. According to the CT values of the pixels and the number of pixels, the noise intensity of the noise in the CT image is calculated.

[0055] According to an embodiment of the present invention, determining the noise intensity of the noise in the CT image based on the CT values of the pixels and the number of pixels includes: determining the noise intensity SD of the noise in the CT image according to formula (1).

[0056] (1)

[0057] where is the CT value of the i-th pixel within the preset region, n is the number of pixels within the preset region, i ≤ n, and both i and n are positive integers.

[0058] According to an embodiment of the present invention, the noise in the CT image generally shows the variation of the CT value in the image with respect to its average value. is the standard deviation of the n pixels in the preset region of the CT image, representing the degree of fluctuation of the CT values of the pixel points within the preset region, that is, the intensity of the noise. The larger this standard deviation, the greater the intensity of the noise.

[0059] In this way, the noise intensity of the noise in the CT image can be determined based on the CT values of the pixels and the number of pixels, providing a data basis for subsequent determination of the training dataset and improving the calculation efficiency.

[0060] According to an embodiment of the present invention, in step S104, based on the noise type and the noise intensity, a training dataset is determined, where the training noise type of the training CT images in the training dataset is the same as the noise type.

[0061] For example, based on the noise type and the noise intensity of the CT image, noises with the same noise type and relatively small differences in noise intensity are simulated and introduced into the training dataset.

[0062] According to an embodiment of the present invention, in step S105, based on the training dataset, a noise processing model is trained to obtain a trained noise processing model.

[0063] According to an embodiment of the present invention, step S105 includes:

[0064] Determining the data volume of each training dataset;

[0065] Determine the pixel values of each pixel in the training CT image;

[0066] Determine the spatial resolution and contrast resolution of the training CT image;

[0067] Obtain a high-quality CT image, and determine the reference pixel value corresponding to the pixel in the training CT image in the high-quality CT image and the reference noise intensity of the high-quality CT image;

[0068] Determine the peak signal-to-noise ratio according to the pixel value and the reference pixel value;

[0069] Process the training CT image through a noise processing model to obtain a processed training CT image;

[0070] Determine the predicted noise intensity of the processed training CT image;

[0071] Determine the training loss function of the noise processing model according to the spatial resolution, the contrast resolution, the peak signal-to-noise ratio, the data volume, the predicted noise intensity and the reference noise intensity;

[0072] Train the noise processing model according to the training loss function to obtain a trained noise processing model.

[0073] For example, each training data set contains multiple CT images for training. Determine the size of each training data set, that is, the data volume of the training data set; determine the pixel values of each pixel in the training CT image through a CT scanner; detect the spatial resolution and contrast resolution of the training CT image through professional testing methods and tools (such as a sine wave test card); select a high-quality CT image as a reference image for the training CT image. The high-quality CT image can be an undamaged image or an image considered to be closest to the real situation after a certain preprocessing. The high-quality CT image has the same resolution as the training CT image, that is, the same number of pixels and arrangement, and obtain the reference pixel value corresponding to the pixel in the training CT image in the high-quality CT image and the reference noise intensity of the high-quality CT image; calculate the peak signal-to-noise ratio according to the pixel value of the training CT image and the reference pixel value of the high-quality CT image; the noise processing model is a deep learning neural network model that can process CT images and output a denoised CT image; detect the noise intensity of the processed training CT image, that is, the predicted noise intensity; determine the training loss function of the noise processing model according to the spatial resolution, the contrast resolution, the peak signal-to-noise ratio, the data volume, the predicted noise intensity and the reference noise intensity; train the noise processing model according to the training loss function to obtain a trained noise processing model.

[0074] According to an embodiment of the present invention, determining the peak signal-to-noise ratio based on the pixel value and the reference pixel value includes: determining the peak signal-to-noise ratio of the k-th training CT image in the j-th training dataset according to formula (2). ,

[0075] (2)

[0076] where max is the maximum value function, is the pixel value of the r-th pixel of the k-th training CT image in the j-th training dataset, is the pixel value of the r-th corresponding pixel of the high-quality CT image corresponding to the k-th training CT image in the j-th training dataset, R is the number of pixels in the training CT image, r ≤ R, and both r and R are positive integers.

[0077] According to an embodiment of the present invention, is the maximum pixel value of the k-th training CT image in the j-th training dataset, is the mean square error, representing the average of the squares of the errors between the signal and the noise, represents the ratio of the maximum possible power to the destructive noise power, that is, the peak signal-to-noise ratio. The larger the peak signal-to-noise ratio, the smaller the noise in the CT image and the higher the quality of the image.

[0078] In this way, the peak signal-to-noise ratio can be determined based on the pixel value and the reference pixel value, improving the convenience of calculation.

[0079] According to an embodiment of the present invention, determining the training loss function of the noise processing model based on the spatial resolution, the contrast resolution, the peak signal-to-noise ratio, the data volume, the predicted noise intensity, and the reference noise intensity includes: determining the training loss function of the noise processing model according to formula (3). ,

[0080] (3)

[0081] where, is the peak signal-to-noise ratio of the k-th training CT image in the j-th training dataset, is the preset peak signal-to-noise ratio threshold, is the spatial resolution of the k-th training CT image in the j-th training dataset, is the preset spatial resolution threshold, is the contrast resolution of the k-th training CT image in the j-th training dataset, is the preset contrast resolution threshold, is the predicted noise intensity of the k-th training CT image in the j-th training dataset, is the reference noise intensity of the high-quality image of the k-th training CT image in the j-th training dataset, is the data volume of the j-th training dataset, m is the number of training datasets, j ≤ m, K is the number of training CT images in the training dataset, k ≤ K, and j, m, k, and K are all positive integers.

[0082] According to an embodiment of the present invention, is the ratio of the spatial resolution of the k-th training CT image in the j-th training dataset to the preset spatial resolution threshold. The larger this ratio, the higher the spatial resolution of the k-th training CT image in the j-th training dataset. is the ratio of the contrast resolution of the k-th training CT image in the j-th training dataset to the preset contrast resolution threshold. The larger this ratio, the higher the contrast resolution of the k-th training CT image in the j-th training dataset. is the ratio of the peak signal-to-noise ratio of the k-th training CT image in the j-th training dataset to the preset peak signal-to-noise ratio threshold. The larger this ratio, the larger the peak signal-to-noise ratio of the k-th training CT image in the j-th training dataset. indicates that the spatial resolution and contrast resolution are positively correlated with the noise intensity, and the peak signal-to-noise ratio is negatively correlated with the noise intensity. For example, the higher the spatial resolution of a CT image, at the same time, due to the reduction in the number of received photons, the noise intensity will also increase accordingly. The higher the contrast resolution of a CT image, at the same time, the higher the exposure conditions, the more X-ray photons are generated, resulting in an increase in the noise intensity and a smaller peak signal-to-noise ratio, and the worse the quality of the image and the higher the noise intensity. is the ratio of the data volume of the j-th training dataset to the average data volume of m training datasets. The larger this ratio, the relatively larger the data volume of the j-th training dataset, the greater the impact on the training process, and the greater the impact of its change on the error of the predicted noise intensity. is the relative error between the predicted noise intensity of the k-th training CT image in the j-th training dataset and the reference noise intensity of the high-quality image of the k-th training CT image in the j-th training dataset.

[0083] According to an embodiment of the present invention, using and to perform weighted averaging on the relative errors of the predicted noise intensities of each training CT image to obtain a training loss function. During the training process, the above training loss function is minimized, so that the error between the predicted noise intensity and the reference noise intensity is reduced, the accuracy of the noise processing model for noise processing is improved, and thus the accuracy of the noise processing model is enhanced.

[0084] In this way, based on the effects of spatial resolution, contrast resolution, and peak signal-to-noise ratio on noise intensity, the impact of the above data on the error of predicting noise intensity can be determined. Then, based on this impact, as well as the relative error of the predicted noise intensity and the data volume of the training dataset, the training loss function is set. During the training process of the noise processing model, the training loss function is reduced, and the trained noise processing model is made more suitable for noise reduction processing of CT images of the current type and intensity, thereby more specifically improving the accuracy of the noise processing model.

[0085] According to an embodiment of the present invention, training the noise processing model according to the training loss function to obtain a trained noise processing model includes:

[0086] Determining the total training amount according to the data volume;

[0087] Determining a first ratio according to the total training amount and a preset training amount threshold;

[0088] Determining the training learning rate according to a preset learning rate threshold and the first ratio;

[0089] Training the noise processing model according to the training loss function and the training learning rate to obtain a trained noise processing model.

[0090] For example, a large-scale dataset can provide rich samples and features, which helps the model learn the broad distribution and potential patterns of the data. For a large-scale dataset, a relatively large learning rate can usually be selected because a larger dataset can provide stable gradient estimates, allowing the model to perform parameter updates with larger step sizes in each iteration. A small-scale dataset has a limited sample size, which may lead to overfitting or underfitting of the model. For a small-scale dataset, a smaller learning rate is usually used to avoid model instability or overfitting of the training data caused by excessive weight updates. The total training amount is determined by summing up the data volumes of each training dataset; the first ratio is determined according to the ratio of the total training amount to the preset training amount threshold, indicating the scale of the dataset. The larger the first ratio, the larger the scale of the dataset, and a relatively larger learning rate should be selected; the training learning rate is determined according to the product of the first ratio and the preset learning rate threshold; the noise processing model is trained according to the training loss function and the training learning rate to obtain a trained noise processing model.

[0091] According to an embodiment of the present invention, in step S106, processing the CT image according to the trained noise processing model to obtain a denoised CT image.

[0092] For example, a trained noise processing model is used to process a CT image to recover a clean image. Through noise reduction processing, the noise level in the CT image can be effectively reduced, the clarity of the image can be improved, which helps to identify the details of the damaged part and enhance the damage recognition ability.

[0093] According to an embodiment of the present invention, in step S107, determine the damage area at the damage position in the noise-reduced CT image, and determine the second CT value of the pixels at the damage position.

[0094] For example, determine the damage area at the damage position in the noise-reduced CT image and the CT value of the pixels at the damage position, that is, the second CT value, through a CT scanner.

[0095] According to an embodiment of the present invention, in step S108, determine the damage severity coefficient according to the damage area and the second CT value.

[0096] According to an embodiment of the present invention, step S108 includes:

[0097] Determine the damage centroid at the damage position;

[0098] Determine the damage shape of the edge at the damage position;

[0099] According to the damage centroid and the damage shape, determine a first similar shape and a second similar shape, wherein the first similar shape and the second similar shape are centered on the damage centroid, and the first similar shape and the second similar shape are the same as the damage shape;

[0100] Determine a first pixel sampling point at the edge of the first similar shape and determine the second CT value of the first pixel sampling point;

[0101] Determine a second pixel sampling point at the edge of the second similar shape and determine the second CT value of the second pixel sampling point;

[0102] Determine the damage severity coefficient according to the second CT value of the first pixel sampling point, the second CT value of the second pixel sampling point and the damage area.

[0103] For example, determine the centroid (i.e., the damage centroid) and the shape (i.e., the damage shape) of the damage location in the CT image; determine the first similar shape and the second similar shape according to the damage centroid and the damage shape. For example, if the damage shape of the edge at the damage location is circular, the first similar shape and the second similar shape are concentric circles with the centroid of the damage location as the center. The radius of the first similar shape is larger, the radius of the second similar shape is smaller, and both the first similar shape and the second similar shape are located within the damage location. For example, if the damage location is a circle with a radius of r, the first similar shape is a circle with a radius greater than 0.5r and less than r, and the second similar shape is a circle with a radius less than 0.5r; perform uniform sampling at the edge of the first similar shape to determine the first pixel sampling points, and detect the CT values of the first pixel sampling points; perform uniform sampling at the edge of the second similar shape to determine the second pixel sampling points, and detect the CT values of the second pixel sampling points; evaluate the damage degree of the damaged part in the CT image according to the second CT values of the first pixel sampling points, the second CT values of the second pixel sampling points, and the damage area, and determine the damage severity coefficient.

[0104] According to an embodiment of the present invention, determining the damage severity coefficient according to the second CT values of the first pixel sampling points, the second CT values of the second pixel sampling points, and the damage area includes: determining the damage severity coefficient according to formula (4) ,

[0105] (4)

[0106] where max is the maximum value function, , and are preset weight values, is the damage area, is the second CT value of the f-th first pixel sampling point, is the second CT value of the f-th second pixel sampling point, is the preset CT value, F is the number of first pixel sampling points, f ≤ F, and both f and F are positive integers.

[0107] According to an embodiment of the present invention, represents the relative difference between the second CT value of the f-th first pixel sampling point and the preset CT value. The larger this ratio is, the greater the change in the second CT value of the f-th first pixel sampling point relative to the preset CT value, and the greater the damage degree at the f-th first pixel sampling point. When damage occurs in a certain part (such as fracture, bleeding, inflammation, etc.), the density of this part may change, resulting in a change in the CT value. When the number of first pixel sampling points with a higher damage degree in the first similar shape is larger, the preset weight value of the corresponding first pixel sampling point is larger, It represents the maximum value of the sum of the products of the damage degrees and corresponding weights of F first pixel sampling points in the first similar shape. For example, when the value at the first first pixel sampling point in the first similar shape is is 1, the value at the second first pixel sampling point is 0.8, the value at the second first pixel sampling point is 0.9, and the preset weights are , and , and , then the value of is , indicating that when there are more first pixel sampling points with higher damage degrees in the first similar shape, the influence on the damage degree at the edge of the first similar shape becomes more severe as the number of first pixel sampling points with higher damage degrees increases. Among them, the preset weight changes in a form combining an exponential function and a linear function. The part of the change of in the form of a linear function indicates that as the damage degree at a single first pixel sampling point increases, the overall damage degree at the edge of the first similar shape increases uniformly. The part of the change of in the form of an exponential function indicates that as the number of first pixel sampling points with higher damage degrees increases, the influence on the overall damage degree at the edge of the first similar shape increases rapidly and not uniformly. The above method of finding the maximum value by distributing weight values can be used to solve the situation where the overall damage degree at the edge of the first similar shape is the most severe, that is, the overall damage situation in the peripheral area of the damage location, which is convenient for evaluating the severity of the patient's condition. Similarly, can be used to solve the situation where the overall damage degree at the edge of the second similar shape is the most severe, that is, the overall damage situation in the central area of the damage location. is to determine the overall damage degree of the damage location based on the overall damage degree in the peripheral area of the damage location and the overall damage degree in the central area of the damage location. Among them, is less than , indicating that the influence degree of the overall damage degree in the central area of the damage location on the overall damage degree of the damage location is relatively large. is to determine the comprehensive damage severity of the damage location based on the overall damage degree of the damage location and the damage area.

[0108] In this way, the severity coefficient of the injury can be determined based on the second CT value of the first pixel sampling point, the second CT value of the second pixel sampling point, and the injury area. During the calculation, the overall most severe injury degree of the peripheral area and the central area in the injury location can be determined according to the injury degree at the pixel sampling points in the similar shape. Further, the overall injury degree of the injury location can be determined based on the overall injury degree of the peripheral area and the central area in the injury location, and combined with the injury area, the comprehensive injury severity of the injury location can be determined, improving the comprehensiveness and accuracy of the injury severity coefficient.

[0109] According to an embodiment of the present invention, in step S109, an injury report is generated based on the injury severity coefficient.

[0110] For example, according to the injury severity coefficient, the injury severity at the injury location is determined to generate an injury report.

[0111] The medical injury CT image processing method according to an embodiment of the present invention can accurately analyze the noise type and noise intensity in a medical injury CT image, determine a training data set according to the noise type and noise intensity to train a noise processing model, and determine the injury area and CT value of the injury site based on the denoised medical injury CT image. Further, the injury degree at the injury location is evaluated according to the injury area and CT value, which is beneficial to improving the accuracy and effectiveness of the detailed analysis of the injury location in the CT image. When determining the noise intensity, the noise intensity of the noise in the CT image can be determined according to the CT value of the pixel and the number of pixels, providing a data basis for subsequent determination of the training data set and improving the calculation efficiency. When determining the peak signal-to-noise ratio, the peak signal-to-noise ratio can be determined according to the pixel value and the reference pixel value, improving the convenience of calculation. When determining the training loss function, the influence of the spatial resolution, contrast resolution, and peak signal-to-noise ratio on the noise intensity can be used to determine the influence of the above data on the error of predicting the noise intensity. Based on this influence, as well as the relative error of the predicted noise intensity and the data volume of the training data set, the training loss function is set, so that during the training process of the noise processing model, the training loss function is reduced, and the trained noise processing model is more suitable for the denoising process of the current type and intensity of CT images, and more specifically improves the accuracy of the noise processing model. When determining the injury severity coefficient, the injury severity coefficient is determined according to the second CT value of the first pixel sampling point, the second CT value of the second pixel sampling point, and the injury area. During the calculation process, the overall most severe injury degree of the peripheral area and the central area in the injury location can be determined according to the injury degree at the pixel sampling point in the similar shape. Further, the overall injury degree of the injury location is determined according to the overall injury degree of the peripheral area and the central area in the injury location, and combined with the injury area, the comprehensive injury severity of the injury location is determined, improving the comprehensiveness and accuracy of the injury severity coefficient.

[0112] Figure 2 Exemplarily, a block diagram of a medical injury CT image processing system according to an embodiment of the present invention is shown. The system includes:

[0113] A preprocessing module for performing data preprocessing on the CT image;

[0114] A noise type module for determining the noise type of the noise in the CT image;

[0115] A noise intensity module for determining the noise intensity of the noise in the CT image;

[0116] A training data module for determining a training data set according to the noise type and the noise intensity, wherein the training noise type of the training CT image in the training data set is the same as the noise type;

[0117] A training model module for training a noise processing model based on the training data set to obtain a trained noise processing model;

[0118] A training model module for processing a CT image according to the trained noise processing model to obtain a denoised CT image;

[0119] An image analysis module for determining the damage area at the damage position in the denoised CT image and determining the second CT value of the pixels at the damage position;

[0120] A damage degree module for determining a damage severity coefficient according to the damage area and the second CT value;

[0121] A damage report module for generating a damage report according to the damage severity coefficient.

[0122] The present invention may be a method, an apparatus, a system, and / or a computer program product. The computer program product may include a computer-readable storage medium having thereon computer-readable program instructions for performing various aspects of the present invention.

[0123] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the drawings are only examples and do not limit the present invention. The object of the present invention has been fully and effectively achieved. The functions and structural principles of the present invention have been shown and described in the embodiments, and the embodiments of the present invention may have any deformation or modification without departing from the principle.

Claims

1. A method for processing medical injury CT images, characterized in that: include: Perform data preprocessing on CT images; Determine the noise type of noise in CT images; Determining the noise intensity of noise in CT images; Determining a training data set according to the noise type and the noise intensity, wherein the training noise type of the training CT image in the training data set is the same as the noise type; According to the training data set, the noise processing model is trained to obtain a trained noise processing model; Processing the CT image according to the trained noise processing model to obtain a denoised CT image; Determine the lesion area at the lesion location in the noise-reduced CT image, and determine a second CT value of the pixel at the lesion location; determining an injury severity coefficient according to the injury area and the second CT value; generating an injury report according to the injury severity coefficient; Determining an injury severity coefficient according to the injury area and the second CT value includes: Determine a damage centroid at the damage location, wherein the damage centroid is the centroid of the area where the damage location is located; determining the damage shape of the edge at the damage location; Determine a first similar shape and a second similar shape according to the damage centroid and the damage shape, wherein the first similar shape and the second similar shape are centered on the damage centroid, and the first similar shape and the second similar shape are the same as the damage shape; Determine a first pixel sampling point at an edge of the first similar shape, and determine a second CT value of the first pixel sampling point; Determine a second pixel sampling point at an edge of the second similar shape, and determine a second CT value of the second pixel sampling point; An injury severity coefficient is determined according to the second CT value of the first pixel sampling point, the second CT value of the second pixel sampling point, and the injury area.

2. The medical injury CT image processing method according to claim 1, characterized in that: Determine the noise intensity of the noise in the CT image, including: In the CT image, a preset area is determined; Obtaining the CT value and number of pixels of each pixel in a preset area; The noise intensity of the noise in the CT image is determined according to the CT value of the pixel and the number of the pixels.

3. The medical injury CT image processing method according to claim 2, characterized in that: Determining the noise intensity of noise in the CT image according to the CT value of the pixel and the number of the pixels includes: According to the formula ； Determine the noise intensity SD of the noise in the CT image, where, is the CT value of the i-th pixel in the preset area, n is the number of pixels in the preset area, i≤n, and both i and n are positive integers.

4. The medical injury CT image processing method according to claim 1, characterized in that: According to the training data set, the noise processing model is trained to obtain a trained noise processing model, including: Determine the amount of data for each training data set; Determining a pixel value of each pixel in the training CT image; Determine the spatial resolution and contrast resolution of the training CT images; Acquire a high-quality CT image, and determine reference pixel values ​​of corresponding pixels in the high-quality CT image and the training CT image and a reference noise intensity of the high-quality CT image; Determining a peak signal-to-noise ratio according to the pixel value and the reference pixel value; Processing the training CT image through the noise processing model to obtain a processed training CT image; determining predicted noise intensity of processed training CT images; Determining a training loss function of a noise processing model according to the spatial resolution, the contrast resolution, the peak signal-to-noise ratio, the data volume, the predicted noise intensity, and the reference noise intensity; The noise processing model is trained according to the training loss function to obtain a trained noise processing model.

5. The medical injury CT image processing method according to claim 4, characterized in that: Determining a peak signal-to-noise ratio according to the pixel value and the reference pixel value includes: According to the formula ； Determine the peak signal-to-noise ratio of the kth training CT image in the jth training dataset , where max is the maximum value function, is the pixel value of the rth pixel of the kth training CT image in the jth training data set, is the pixel value of the rth corresponding pixel of the high-quality CT image corresponding to the kth training CT image in the jth training data set, R is the number of pixels in the training CT image, r≤R, and r and R are both positive integers.

6. The medical injury CT image processing method according to claim 4, characterized in that: Determining a training loss function of a noise processing model according to the spatial resolution, the contrast resolution, the peak signal-to-noise ratio, the data volume, the predicted noise intensity, and the reference noise intensity includes: According to the formula ； Determine the training loss function for the noise processing model ,in, is the peak signal-to-noise ratio of the kth training CT image in the jth training dataset, is the preset peak signal-to-noise ratio threshold, is the spatial resolution of the kth training CT image in the jth training dataset, is the preset spatial resolution threshold, is the contrast resolution of the kth training CT image in the jth training dataset, is the preset contrast resolution threshold, is the predicted noise intensity of the kth training CT image in the jth training dataset, is the reference noise intensity of the high-quality image of the k-th training CT image in the j-th training dataset, is the data size of the jth training data set, m is the number of training data sets, j≤m, K is the number of training CT images in the training data set, k≤K, j, m, k and K are all positive integers.

7. The medical injury CT image processing method according to claim 4, characterized in that: The noise processing model is trained according to the training loss function to obtain a trained noise processing model, including: Determining a total training amount based on the data amount; Determining a first ratio according to the total training amount and a preset training amount threshold; Determining a training learning rate according to a preset learning rate threshold and the first ratio; The noise processing model is trained according to the training loss function and the training learning rate to obtain a trained noise processing model.

8. The medical injury CT image processing method according to claim 1, characterized in that: Determining the injury severity coefficient according to the second CT value of the first pixel sampling point, the second CT value of the second pixel sampling point, and the injury area includes: According to the formula ； Determining the Injury Severity Factor , where max is the maximum value function, , and is the preset weight, is the damaged area, is the second CT value of the fth first pixel sampling point, is the second CT value of the f-th second pixel sampling point, is the preset CT value, F is the number of the first pixel sampling points, f≤F, and both f and F are positive integers.

9. A medical injury CT image processing system for executing the method according to any one of claims 1 to 8, characterized in that: include: A preprocessing module, used for performing data preprocessing on CT images; A noise type module, used to determine the noise type of noise in the CT image; A noise intensity module for determining the noise intensity of noise in the CT image; A training data module, used to determine a training data set according to the noise type and the noise intensity, wherein the training noise type of the training CT image in the training data set is the same as the noise type; A training model module, used to train the noise processing model according to the training data set to obtain a trained noise processing model; A training model module, used to process the CT image according to the trained noise processing model to obtain a denoised CT image; An image analysis module, used to determine the damage area at the damage position in the CT image after noise reduction, and determine the second CT value of the pixel at the damage position; An injury severity module, used to determine an injury severity coefficient according to the injury area and the second CT value; The damage report module is used to generate a damage report according to the damage severity coefficient.

Images