Artificial Intelligence-Assisted CT Image Quality Enhancement and Noise Reduction Method

Abstract

The present invention relates to the field of image processing technology, and particularly to an artificial intelligence-assisted CT image quality enhancement and noise reduction method, which includes the following steps: S1: Obtain low-dose CT scan image data; S2: Preprocess the obtained low-dose CT image data; S3: Extract preliminary feature information in the CT image; S4: Perform adaptive estimation of the noise in the image; S5: Input the noise estimation result and the preliminary feature information into a deep convolutional denoising network together; S6: Enhance the quality of the denoised image based on the generative adversarial network framework; S7: Reconstruct the CT image with enhanced quality; S8: Perform medical applicability detection on the final image. With the present invention, through the generative adversarial network, convolutional neural network and medical image discrimination model, denoising and quality enhancement of low-dose CT images are achieved, CT images with high signal-to-noise ratio and high structural fidelity are generated, and at the same time, its medical applicability is ensured to meet the clinical diagnosis requirements.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and particularly to an artificial intelligence-assisted CT image quality enhancement and noise reduction method. Background Art

[0002] With the wide application of computed tomography (CT) technology, CT images have become an indispensable important tool in medical diagnosis, especially showing significant advantages in detecting early lesions and precise positioning. However, in order to reduce the potential harm of radiation to patients, low-dose CT scans are increasingly being used. However, although low-dose CT reduces the radiation dose, it brings about a decrease in the signal-to-noise ratio of the image and a reduction in image quality. Traditional image post-processing methods attempt to improve image quality through filtering or enhancement techniques, but often result in the loss of image details or the introduction of artifacts during the denoising process, making it difficult to ensure the reliability of the image in diagnosis. Existing image processing technologies are difficult to effectively improve image quality while maintaining the integrity of the image structure. Especially under low-dose CT conditions, the balance between image quality and signal-to-noise ratio has always been a technical problem.

[0003] The existing technologies mainly rely on rule design or simple convolutional neural network models. Although they can achieve a certain degree of denoising and image enhancement, when processing CT images, it is difficult to simultaneously consider the distribution characteristics of noise and the structural features of the image, resulting in the final generated images often not meeting the high standards of clinical diagnosis. In addition, there is a lack of automated means for the medical applicability detection of images, and doctors need to manually evaluate the image quality, increasing the workload. Therefore, an artificial intelligence-based CT image quality enhancement and noise reduction method is proposed to solve the problems of the quality and diagnostic accuracy of low-dose CT images. Summary of the Invention

[0004] Based on the above purposes, the present invention provides an artificial intelligence-assisted CT image quality enhancement and noise reduction method.

[0005] The artificial intelligence-assisted CT image quality enhancement and noise reduction method includes the following steps:

[0006] S1: Obtain low-dose CT scan image data, where the image data includes two-dimensional tomographic images collected by a CT device under low-dose conditions;

[0007] S2: Preprocess the obtained low-dose CT image data, and the preprocessing includes normalizing, artifact removal, and edge smoothing processing of the image data;

[0008] S3: Based on the preprocessed image data, extract preliminary feature information in the CT image, and the feature information includes the edges, textures, and gray-scale distributions of the image;

[0009] S4: Input the extracted preliminary feature information into a convolutional neural network model to adaptively estimate the noise in the image. The convolutional neural network model generates feature weights related to the image noise by learning the noise distribution characteristics in the CT image to guide the denoising operation;

[0010] S5: Input the noise estimation result and the preliminary feature information into a deep convolutional denoising network. The denoising network consists of multiple convolutional and deconvolutional operations and is used to remove the image noise;

[0011] S6: Enhance the quality of the denoised image based on the generative adversarial network framework. The generative adversarial network includes a generator and a discriminator. The generator is used to generate enhanced CT images, and the discriminator is used to evaluate the similarity between the enhanced image and the standard high-dose image;

[0012] S7: Reconstruct the quality-enhanced CT image to generate a final image output with high signal-to-noise ratio and high structural fidelity;

[0013] S8: Conduct a medical applicability test on the final image, and automatically evaluate the image through a trained medical image discrimination model.

[0014] Optionally, the specific steps of S1 include:

[0015] S11: Set the low-dose scanning parameters of the CT device. The scanning parameters include the X-ray tube voltage, tube current, and exposure time. The range of the tube voltage is controlled between 80 kVp and 120 kVp, the range of the tube current is controlled between 10 mA and 50 mA, and the exposure time is 1.5 seconds;

[0016] S12: Start the CT device based on the set low-dose scanning parameters, emit a low-dose X-ray beam through the X-ray tube, and receive the attenuation information after passing through the human body through the detector;

[0017] S13: Convert the received attenuation information into a two-dimensional tomographic image through the reconstruction algorithm in the CT device. The reconstruction algorithm uses the filtered back-projection technique, and the specific formula is: , where, represents the reconstructed two-dimensional tomographic image, and are the coordinate positions of the image; represents the projection data received at the projection angle and the projection distance ; represents the projection angle; represents the projection path distance; represents the convolution kernel of the filtering function acting on the projection data, where is the projection path coordinate; and are the cosine and sine functions of the projection angle respectively; is the integration variable, representing the cumulative weight of the image points along different projection angles for the image points.

[0018] Optionally, the S2 specifically includes:

[0019] S21: Perform normalization processing on the obtained low-dose CT image data, adjust the gray value of the image data to a predetermined range, so that the gray values of all pixels are between 0 and 1;

[0020] S22: Perform artifact removal processing on the normalized image, based on the bilateral filtering algorithm, through joint smoothing processing of the space and pixel intensity of the image;

[0021] S23: Perform edge smoothing processing on the image after artifact removal, by applying Gaussian smoothing filtering technology to remove high-frequency noise in the image.

[0022] Optionally, the S3 specifically includes:

[0023] S31: Extract edge features from the preprocessed image data, specifically using a gradient-based edge detection algorithm, by calculating the change rate of the pixel gray values in the image to identify the regions where the gray values change sharply in the image;

[0024] S32: Extract texture features from the image after edge feature extraction, using the gray-level co-occurrence matrix analysis method, by statistically analyzing the co-occurrence relationship of adjacent pixel gray values to extract local texture information in the image, including the directionality, roughness, and repeatability of the texture;

[0025] S33: While extracting texture features, extract the gray value distribution features of the image, calculate the overall gray value distribution of the image, and obtain the distribution of bright and dark regions in the image by statistically analyzing the gray histogram of the pixels.

[0026] Optionally, the S4 specifically includes:

[0027] S41: Input the extracted preliminary feature information into a pre-trained convolutional neural network model, which consists of multiple convolutional layers, pooling layers, and fully connected layers, and extract image features at different scales through convolutional operations;

[0028] S42: In the convolutional layer, the convolutional kernel scans the input image features pixel by pixel and calculates the feature response of the local region;

[0029] S43: In the pooling layer, the data dimension is reduced through downsampling operations to extract image features while preserving the key noise patterns of the image;

[0030] S44: After multiple layers of convolution and pooling, it enters the fully connected layer for calculating feature weights. Through adaptive learning of the feature weights, a feature weight matrix related to noise is generated, and the feature weight matrix is used to reflect the intensity, distribution, and location of noise in the image;

[0031] S45: Finally, by outputting the feature weight matrix, the convolutional neural network can adaptively estimate the noise in the image and generate a corresponding noise distribution model.

[0032] Optionally, the specific steps of S5 are as follows:

[0033] S51: Use the noise estimation result and the preliminary feature information as inputs and input them into the deep convolutional denoising network. The preliminary feature information includes the edges, textures, and gray-scale distributions of the image, while the noise estimation result represents the noise distribution at each pixel position in the image;

[0034] S52: In the deep convolutional denoising network, use multiple layers of convolution operations to jointly process the noise estimation result and the preliminary feature information. The joint processing synthesizes the noise and feature information in the image through convolution operations, enabling the denoising process to consider the structural features of the image and extract the joint distribution of noise and features;

[0035] S53: Perform deconvolution operations on the image features after convolution processing to map the extracted high-dimensional features back to the spatial dimension of the original image and generate a denoised image;

[0036] S54: Perform weight fusion on the denoised image obtained by deconvolution and the preliminary feature information, and balance the denoising effect and the retention of image detail features by adjusting the weight ratio, thereby generating the final denoised image.

[0037] Optionally, the specific steps of S6 are as follows:

[0038] S61: Input the denoised CT image into the generator in the generative adversarial network framework. The generator is a convolutional neural network structure that extracts and enhances the detail features in the input denoised image through convolution and deconvolution operations;

[0039] S62: The generator extracts the feature information in the denoised image through multiple convolutional layers and gradually adjusts the details in the image;

[0040] S63: Input the enhanced CT image generated into the discriminator. The discriminator compares the enhanced image with a preset standard image, calculates the difference between the two, and outputs a similarity score;

[0041] S64: Based on the feedback from the discriminator, the generator will optimize the image generation process. By continuously adjusting the weights of the convolutional kernels, it maximizes the similarity between the enhanced image and the standard image, and then the training of the adversarial network is optimized through multiple iterations, and the output gradually approaches the quality of the standard high-dose CT image.

[0042] Optionally, the specific content of S63 includes:

[0043] S631: Take the generated enhanced CT image and the preset standard high-dose CT image as inputs, and send them into the convolutional neural network structure of the discriminator respectively. Through convolutional operations, extract the feature vectors of the enhanced image and the standard image respectively;

[0044] S632: The discriminator compares the feature vectors of the enhanced image and the standard image, calculates the difference between the two, and obtains the overall difference value of the two images in the feature space by comparing the feature differences of each pixel point;

[0045] S633: According to the calculated difference value, calculate the similarity score. The similarity score represents the matching degree between the enhanced image and the standard image. The higher the score, the closer the two are in terms of details and structure.

[0046] Optionally, the specific content of S7 includes:

[0047] S71: Take the CT image with enhanced quality as the input, send it into the image reconstruction module, and reconstruct the image through the filtered back-projection technique;

[0048] S72: During the reconstruction process, use the high signal-to-noise ratio optimization algorithm to optimize the reconstructed image;

[0049] S73: Use the structure fidelity optimization algorithm to ensure the detail and structure fidelity of the reconstructed image, specifically by calculating the structural similarity index of the image to optimize the image quality.

[0050] Optionally, the specific content of S8 includes:

[0051] S81: Input the finally reconstructed CT image into the trained medical image discrimination model;

[0052] S82: The discrimination model extracts the features of the input CT image through multiple convolutional layers and pooling layers, and extracts the structural information, texture features and gray-scale distribution in the image;

[0053] S83: The discrimination model inputs the extracted image features into the preset classification algorithm through the classification layer to evaluate the diagnostic applicability of the image;

[0054] S84: According to the classification result, the discrimination model outputs a medical applicability score ranging from 0 to 1, which is used to reflect whether the image is suitable for clinical diagnosis. If the score reaches the preset threshold, it indicates that the CT image meets the requirements of clinical diagnosis.

[0055] Advantages of the present invention:

[0056] In the present invention, by introducing a generative adversarial network and a convolutional neural network model, denoising and quality enhancement are performed on low-dose CT images. The generator extracts and enhances the detailed features in the image through multi-layer convolutional and deconvolution operations, and the discriminator compares the generated image with the standard high-dose image and outputs a similarity score, gradually optimizing the quality of the generated CT image.

[0057] In the present invention, through a high signal-to-noise ratio optimization algorithm and a structure fidelity optimization algorithm, important features such as the edges and textures of the image can be maintained while removing noise, and the generated CT image has a high signal-to-noise ratio and high structure fidelity.

[0058] In the present invention, by automatically extracting image features and performing multi-dimensional evaluation on the quality, noise level, and structural integrity of the image, the discrimination model can quickly and accurately output an applicability score to ensure that the generated CT image meets the clinical diagnosis requirements. Description of the drawings

[0059] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only those of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0060] Figure 1 Schematic diagram of the CT image quality enhancement and noise reduction method according to the embodiment of the present invention;

[0061] Figure 2 Schematic diagram of the process for adaptively estimating the noise in the image according to the embodiment of the present invention. Detailed implementation manners

[0062] As Figure 1 - Figure 2 shown, the artificial intelligence-assisted CT image quality enhancement and noise reduction method includes the following steps:

[0063] S1: Obtain low-dose CT scan image data, where the image data includes two-dimensional tomographic images collected by a CT device under low-dose conditions;

[0064] S2: Preprocess the acquired low-dose CT image data. The preprocessing includes normalizing the image data, removing artifacts, and performing edge smoothing to optimize the basic quality of the image data and provide a good input basis for subsequent steps;

[0065] S3: Based on the preprocessed image data, extract the preliminary feature information in the CT image. The feature information includes the edges, textures, and gray-scale distributions of the image, ensuring that the image structure information is fully retained;

[0066] S4: Input the extracted preliminary feature information into a convolutional neural network model to perform an adaptive estimation of the noise in the image. The convolutional neural network model generates feature weights related to the image noise by learning the noise distribution characteristics in the CT image to guide the denoising operation;

[0067] S5: Input the noise estimation result and the preliminary feature information into a deep convolutional denoising network. The denoising network consists of multiple convolutional and deconvolutional operations, which are used to remove the image noise while keeping the image structure information intact;

[0068] S6: Enhance the quality of the denoised image based on the generative adversarial network framework. The generative adversarial network includes a generator and a discriminator. The generator is used to generate enhanced CT images, and the discriminator is used to evaluate the similarity between the enhanced image and the standard high-dose image to optimize the output of the generator;

[0069] S7: Reconstruct the quality-enhanced CT image to generate a final image output with high signal-to-noise ratio and high structural fidelity, ensuring that the clarity and detail fidelity of the image meet the diagnostic requirements;

[0070] S8: Perform medical applicability detection on the final image. Automatically evaluate the image through a trained medical image discriminant model to ensure that the generated CT image meets the needs of clinical diagnosis.

[0071] S1 specifically includes:

[0072] S11: Set the low-dose scanning parameters of the CT device. The scanning parameters include the X-ray tube voltage, tube current, and exposure time. The range of the tube voltage is controlled between 80 kVp and 120 kVp, the range of the tube current is controlled between 10 mA and 50 mA, and the exposure time is 1.5 seconds, ensuring that the CT scan is completed under low-dose conditions to reduce the impact of radiation on patients;

[0073] S12: Start the CT device based on the set low-dose scanning parameters, emit a low-dose X-ray beam through the X-ray tube, and receive the attenuation information after passing through the human body through the detector;

[0074] S13: Convert the received attenuation information into a two-dimensional tomographic image through the reconstruction algorithm in the CT device. The reconstruction algorithm uses the filtered back-projection technique, and the specific formula is: , where represents the reconstructed two-dimensional tomographic image, and are the coordinate positions of the image; represents at the projection angle and the projection distance the projection data received; represents the projection angle; represents the projection path distance; represents the convolution kernel of the filter function acting on the projection data, where is the projection path coordinate; and are the cosine and sine functions of the projection angle respectively, used to calculate the corresponding projection direction; is the integration variable, representing the cumulative weight of the image points along different projection angles ; By performing filtering and back-projection operations on all projection data, a complete CT two-dimensional tomographic image is obtained; Through the above steps, CT scan image data can be efficiently acquired under low-dose conditions, ensuring a reduction in the impact of radiation dose on patients, while ensuring the integrity and accuracy of the image data, providing a high-quality input basis for subsequent image processing and noise reduction.

[0075] S2 specifically includes:

[0076] S21: Normalize the acquired low-dose CT image data, adjust the gray value of the image data to a predetermined range, so that the gray values of all pixels are between 0 and 1, thereby optimizing the contrast of the image and standardizing the data, ensuring the consistency between different images, and facilitating the implementation of subsequent processing steps; Normalization means adjusting the gray value of the image data to a predetermined range, specifically adjusting the gray value of each pixel through the formula: , where represents the gray value at the position in the image; represents the normalized gray value; and are the minimum and maximum gray values in the image respectively;

[0077] S22: Perform artifact removal on the normalized image. Based on the bilateral filtering algorithm, through the joint smoothing processing of the space and pixel intensity of the image, while removing artifacts, retain the important edges and structure information in the image, ensure the clarity of the image while removing artifacts; The specific filtering process is as follows: , where is the image after artifact removal; is the pixel value at position in the image; is the normalization factor used to normalize the output of the filter; is the filtering window; and are the spatial and pixel intensity standard deviations of the filter, used to control the intensity of filtering smoothness;

[0078] S23: Perform edge smoothing on the image after artifact removal. By applying Gaussian smoothing filtering technology, remove the high-frequency noise in the image, make the image edge transition natural, and at the same time keep the structural information of the image clear to reduce the interference of noise in the subsequent processing process; the specific smoothing formula is: , where represents the Gaussian filter; is the standard deviation of the Gaussian filter, used to control the smoothing intensity; and are the image coordinates; through the above preprocessing steps, including normalization, artifact removal, and edge smoothing, the quality of low-dose CT images can be effectively improved, the influence of artifacts and noise can be reduced, and the image is ensured to have higher clarity and contrast, laying a good foundation for subsequent image enhancement and noise removal operations.

[0079] S3 specifically includes:

[0080] S31: Extract edge features from the preprocessed image data. Specifically, use a gradient-based edge detection algorithm. By calculating the change rate of pixel gray values in the image, identify the regions where the gray values change sharply in the image. The extracted edge information is used to reflect the contours of the structures of organs and tissues in the CT image; the specific edge detection formula is: , where represents the edge intensity at position ; represents the image gray value at position ; and are the gray gradients of the image in the direction and direction respectively; by calculating the gray gradients of each pixel, identify the change of gray values at the edge positions in the image, so as to extract the edge features of the image;

[0081] S32: Extract the texture features from the image after edge feature extraction. Using the gray-level co-occurrence matrix analysis method, by statistically analyzing the co-occurrence relationship of the gray values of adjacent pixels, extract the local texture information in the image, including the directionality, roughness, and repeatability of the texture. These texture features can reflect the detailed information of the tissues in the CT image; the specific calculation formula for the texture features is: , where represents the texture feature value of the image; represents the gray value and the joint probability between; and respectively represent the gray values of the pixels;

[0082] S33: While extracting the texture features, extract the gray-level distribution features of the image, calculate the overall gray-level value distribution of the image, and obtain the distribution of bright and dark regions in the image by statistically analyzing the gray-level histogram of the pixels, so as to reflect the density differences of different tissues in the CT image; the formula for calculating the overall gray-level value distribution of the image is: , where represents the gray value the relative frequency in the image; represents the gray value of the number of pixels; represents the total number of pixels in the image; The above steps can accurately extract the edge, texture, and gray-level distribution features in the CT image by using gradient edge detection, gray-level co-occurrence matrix analysis, and gray-level histogram techniques. These features provide detailed information for subsequent noise estimation and denoising processing, ensuring that the image maintains high quality and structural integrity during the noise removal process.

[0083] S4 specifically includes:

[0084] S41: Input the extracted preliminary feature information, including the edge, texture, and gray-level distribution of the image, into a pre-trained convolutional neural network (CNN) model. The convolutional neural network model consists of multiple convolutional layers, pooling layers, and fully connected layers. Extract image features at different scales through convolutional operations, while retaining the local and global information of the image;

[0085] S42: In the convolutional layer, the convolutional kernel scans the input image features pixel by pixel and calculates the feature response of the local region. Through multiple convolutional operations, the noise patterns and structural information in the image can be captured. The weights of the convolutional kernel are optimized through a large-scale training dataset, enabling the network to adaptively learn the distribution characteristics of different types of noise in the CT image;

[0086] S43: In the pooling layer, the data dimension is reduced through downsampling operations to extract concise image features while retaining the key noise patterns of the image. The pooling layer can reduce the computational complexity and enhance the generalization ability of the model to avoid overfitting;

[0087] S44: After multiple layers of convolution and pooling, it enters the fully connected layer for calculating feature weights. Through adaptive learning of the feature weights, a feature weight matrix related to noise is generated. The feature weight matrix is used to reflect the intensity, distribution, and location of noise in the image;

[0088] S45: Finally, by outputting the feature weight matrix, the convolutional neural network can adaptively estimate the noise in the image and generate a corresponding noise distribution model. This noise distribution model is used to guide subsequent denoising operations to ensure that while removing noise, the structure and detail information in the image are retained.

[0089] The specific calculation process for the above adaptive estimation of noise in the image is as follows:

[0090] First, the extracted preliminary feature information is input into the convolutional neural network model;

[0091] Then, in the convolutional layer, a convolutional kernel is used to perform a convolution operation on the input feature information. Specifically: , where represents the convolved feature value; represents the weight of the convolutional kernel at position ; represents the value of the input feature in the neighborhood ; represents the size of the convolutional kernel, which controls the receptive field range. Through multiple layers of convolution operations, the model can capture the noise patterns and structural information in the image;

[0092] Next, in the pooling layer, the convolution result is downsampled. The maximum pooling method is used to calculate the maximum value in each region to reduce the data dimension. The specific formula is: , where is the pooled feature value; is the size of the pooling window, which determines the region range for each sampling. The pooling layer is used to reduce the size of the feature map, retain the key features of the noise, and at the same time reduce the computational complexity;

[0093] Then, the feature map after convolution and pooling is input into the fully connected layer to generate the feature weight matrix , and its calculation process is: , where is the weight function in the fully connected layer, which is used to calculate the noise feature weights;

[0094] Finally, based on the feature weight matrix generate a noise distribution model , specifically: , where represents the noise estimation value at position ; is the noise feature weight matrix; is the pooled eigenvalue. Through the above calculations, a noise distribution model is obtained. This model is used to guide subsequent denoising operations. Through the above steps, by using a convolutional neural network model to adaptively estimate image noise, the noise features in CT images can be accurately captured, a feature weight matrix related to noise can be generated, and the model can perform denoising operations according to the noise distribution in the image, ensuring that the noise is effectively removed while retaining the structural information of the image, improving the image quality. This adaptive denoising method based on feature weights significantly improves the accuracy and image fidelity during the denoising process.

[0095] S5 specifically includes:

[0096] S51: Take the noise estimation result and the preliminary feature information as inputs and input them into the deep convolutional denoising network. The preliminary feature information includes the edges, textures, and gray-scale distributions of the image, while the noise estimation result represents the noise distribution at each pixel position in the image;

[0097] S52: In the deep convolutional denoising network, use multi-layer convolutional operations to jointly process the noise estimation result and the preliminary feature information. The joint processing synthesizes the noise and feature information in the image through convolutional operations, enabling the denoising process to consider the structural features of the image and extract the joint distribution of noise and features;

[0098] S53: Perform deconvolution operations on the image features after convolutional processing to map the extracted high-dimensional features back to the spatial dimension of the original image and generate the denoised image. The deconvolution operation can restore the original resolution of the image and retain the denoising information extracted during the convolution process;

[0099] S54: Perform weight fusion on the denoised image obtained by deconvolution and the preliminary feature information, and balance the denoising effect and the retention of image detail features by adjusting the weight ratio to generate the final denoised image. Through the joint processing of the noise estimation result and the preliminary feature information, the above steps can effectively remove the noise in the image using the deep convolutional denoising network and retain the structural information of the image. The finally generated denoised image has higher quality and is suitable for subsequent image quality enhancement and diagnostic applications.

[0100] The specific calculation process for removing image noise is as follows:

[0101] First, the noise estimation result and the preliminary feature information are used as inputs and fed into the deep convolutional denoising network;

[0102] Then, in the deep convolutional denoising network, through multi-layer convolution operations, the noise estimation result and the preliminary feature information are jointly processed. The specific form of the convolution operation is: , where represents the denoised image features; is the convolution kernel weight in the denoising network, which is optimized for the joint distribution of noise and features; is the noise estimation result; is the preliminary feature information; is the size of the convolution kernel, which controls the range of the receptive field;

[0103] Next, an anti-convolution operation is performed on to reconstruct the denoised image. The anti-convolution process maps the high-dimensional features back to the spatial dimension of the original image. The specific anti-convolution operation is: , where is the pixel value of the anti-convolution output image at coordinate , that is, the restored image result; is the weight of the anti-convolution operation; is the output feature map of the convolution stage of the denoising network, that is, the feature value at position , ;

[0104] Finally, by performing weighted fusion on the anti-convolution result and the preliminary feature information , the final denoised image is generated; the fusion process controls the balance between features and denoising information through the weight coefficient . The specific formula is: , where is the final denoised image; is the fusion weight, which controls the balance between denoising information and preliminary features; is the image after anti-convolution; is the preliminary feature information.

[0105] S6 specifically includes:

[0106] S61: Input the denoised CT image into the generator in the generative adversarial network (GAN) framework. The generator is a convolutional neural network structure. It extracts and enhances the detailed features in the image through convolutional and deconvolutional operations on the input denoised image. The output of the generator is the enhanced CT image, which retains the detailed information of the original image and improves the overall image quality at the same time.

[0107] S62: The generator extracts the feature information in the denoised image through multiple convolutional layers and gradually adjusts the details in the image. The weights of the convolutional kernels are optimized according to a large-scale training dataset, which can identify and amplify the key image features during the generation process, so as to generate a clearer and more structurally complete CT image.

[0108] S63: Input the generated enhanced CT image into the discriminator. The discriminator compares the enhanced image with a preset standard image, calculates the difference between the two, and outputs a similarity score. This score reflects the degree of closeness of the enhanced image to the standard high-dose CT image in multiple dimensions, ensuring that the generated image meets the quality standards required for clinical use.

[0109] S64: Based on the feedback of the discriminator, the generator will optimize the image generation process. By continuously adjusting the weights of the convolutional kernels, it maximizes the similarity between the enhanced image and the standard image. Then, through multiple iterations of optimization in the training of the generative adversarial network, the output gradually approaches the quality of the standard high-dose CT image. The above steps can effectively enhance the quality of the denoised CT image through the collaborative work of the generator and discriminator in the generative adversarial network. The enhanced image generated by the generator undergoes a similarity evaluation by the discriminator to achieve the quality effect of high-quality CT images. This method not only improves the details and contrast of the CT image, but also ensures the overall structural fidelity of the image through the feedback of the discriminator, and is applicable to the generation of high-quality CT images for clinical diagnosis.

[0110] S63 specifically includes:

[0111] S631: Take the generated enhanced CT image and the preset standard high-dose CT image as inputs and send them into the convolutional neural network structure of the discriminator respectively. Through convolutional operations, extract the feature vectors of the enhanced image and the standard image respectively, which are used to describe the detailed features and overall structural information in the image.

[0112] S632: The discriminator compares the feature vectors of the enhanced image and the standard image, calculates the difference between the two, and obtains the overall difference value of the two images in the feature space by comparing the feature differences of each pixel point.

[0113] S633: Calculate a similarity score based on the calculated difference value. The similarity score represents the degree of matching between the enhanced image and the standard image. The higher the score, the closer the two are in terms of details and structure.

[0114] The specific steps for calculating the difference between the two in S63 are as follows:

[0115] First, take the generated enhanced CT image and the preset standard high-dose CT image as inputs and send them into the convolutional neural network structure of the discriminator. After the two images are processed through multiple convolutional layers, their feature vectors are respectively extracted, which are and ;

[0116] Then, by calculating the difference between the feature vectors of the generated image and the standard image, define the difference function between them. The specific difference formula is: where, is the feature difference degree between the enhanced image and the standard image; represents the feature vector of the enhanced image; represents the feature vector of the standard image; is the image coordinate;

[0117] Next, according to the difference degree , calculate the similarity score of the image. The similarity score is used to evaluate the matching degree of the two images. The calculation formula is: where, represents the similarity score between the enhanced image and the standard image, and its value range is from 0 to 1. The closer it is to 1, the more similar the images are; is the maximum difference degree of all training images in the system and is used for normalization processing. The above steps can accurately evaluate the image quality by comparing the feature vectors of the enhanced image and the standard high-dose CT image and using the difference degree function to calculate the difference between the two, and output the similarity score. This scoring mechanism can provide feedback for the generative adversarial network, making the generated enhanced CT image gradually approach the quality of the standard image and ensuring that the fidelity of the image structure and detail features meets the clinical requirements.

[0118] S7 specifically includes:

[0119] S71: Take the CT image with enhanced quality as the input, send it into the image reconstruction module, and reconstruct the image through the filtered back projection (FBP) technique;

[0120] S72: During the reconstruction process, a high signal-to-noise ratio optimization algorithm is used to optimize the reconstructed image. This optimization algorithm calculates the signal-to-noise ratio (SNR) of the image, and the specific calculation formula is: , where represents the power of the signal; represents the power of the noise; the algorithm adjusts the reconstruction parameters according to the SNR value to ensure that noise interference is minimized during the reconstruction process;

[0121] S73: Use a structure fidelity optimization algorithm to ensure the details and structure fidelity of the reconstructed image. Specifically, the image quality is optimized by calculating the structural similarity index (SSIM) of the image. The similarity index calculation formula is: , where and are the means of the images and ; and are the variances of the images and ; is the covariance between the images and ; and are constants to avoid division by zero; through the filtered back-projection algorithm, high signal-to-noise ratio optimization, and structure fidelity optimization algorithms, the above steps can achieve precise reconstruction of the quality-enhanced CT image and output a final image with high signal-to-noise ratio and high structure fidelity.

[0122] When the SNR value increases, it indicates that the effective signal significantly exceeds the noise power at the power level; in the solution of the present invention, when SNR ≥ 30 dB, it is regarded as a high signal-to-noise ratio;

[0123] Reaching this threshold can ensure:

[0124] The error between the CT pixel gray value and the true linear attenuation coefficient is controlled within 3%;

[0125] The contrast attenuation of the 0.5 mm line pair resolution target does not exceed 5%.

[0126] Therefore, in the present invention, the high signal-to-noise ratio is sufficient for the effective signal to have an advantage over the noise to ensure that details, textures, and density gradients in the image can be presented without bias.

[0127] S8 specifically includes:

[0128] S81: Input the finally reconstructed CT image into the trained medical image discrimination model, where the discrimination model is a convolutional neural network model based on deep learning. Through learning a large amount of medical image data, the model can automatically identify the features of CT images and evaluate whether they meet the clinical diagnosis criteria;

[0129] S82: The discrimination model extracts features from the input CT image through multiple convolutional layers and pooling layers, extracting the structural information, texture features, and gray-scale distribution in the image for comparison with the preset medical standards;

[0130] S83: The discrimination model inputs the extracted image features into a preset classification algorithm through the classification layer to evaluate the diagnostic applicability of the image. The classification algorithm scores based on multiple dimensions such as image quality, noise level, structural integrity, and detail fidelity, specifically including evaluation criteria such as signal-to-noise ratio and structural similarity index;

[0131] S84: According to the classification result, the discrimination model outputs a medical applicability score, with the score range from 0 to 1, which is used to reflect whether the image is suitable for clinical diagnosis. If the score reaches the preset threshold, it indicates that the CT image meets the clinical diagnosis requirements.

[0132] This invention covers any substitutions, modifications, equivalent methods, and solutions made within the essence and scope of this invention. To enable the public to have a thorough understanding of this invention, specific details are elaborated in the following preferred embodiments of this invention. However, those skilled in the art can fully understand this invention even without the description of these details. Additionally, to avoid unnecessary confusion to the essence of this invention, well-known methods, processes, procedures, components, and circuits, etc. are not described in detail.

[0133] The above are only the preferred embodiments of this invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of this invention, several improvements and refinements can still be made, and these improvements and refinements should also be regarded as the protection scope of this invention.

Claims

1. An artificial intelligence-assisted CT image quality enhancement and noise reduction method, characterized in that, Including the following steps: S1: Obtain low-dose CT scan image data, where the image data contains two-dimensional tomographic images collected by a CT device under low-dose conditions; S2: Preprocess the obtained low-dose CT image data, and the preprocessing includes normalizing, artifact removal, and edge smoothing of the image data; S3: Based on the preprocessed image data, extract preliminary feature information in the CT image, and the feature information includes the edges, textures, and gray-scale distributions of the image; S4: Input the extracted preliminary feature information into a convolutional neural network model to perform adaptive estimation of the noise in the image. The convolutional neural network model generates feature weights related to the image noise by learning the noise distribution characteristics in the CT image to guide the denoising operation; S5: Input the noise estimation result and the preliminary feature information into a deep convolutional denoising network, and the denoising network consists of multiple convolutional and deconvolutional operations for removing image noise; S6: Enhance the quality of the denoised image based on the generative adversarial network framework. The generative adversarial network includes a generator and a discriminator. The generator is used to generate enhanced CT images, and the discriminator is used to evaluate the similarity between the enhanced image and the standard high-dose image; S7: Reconstruct the CT image with enhanced quality to generate a final image output with high signal-to-noise ratio and high structural fidelity; S8: Perform medical applicability detection on the final image, and automatically evaluate the image through a trained medical image discrimination model.

2. The method for enhancing CT image quality and reducing noise assisted by artificial intelligence according to claim 1, wherein The specific content of S1 includes: S11: Set the low-dose scan parameters of the CT device. The scan parameters include the X-ray tube voltage, tube current, and exposure time. Among them, the range of the tube voltage is controlled between 80 kVp and 120 kVp, the range of the tube current is controlled between 10 mA and 50 mA, and the exposure time is 1.5 seconds; S12: Start the CT device based on the set low-dose scan parameters, emit a low-dose X-ray beam through the X-ray tube, and receive the attenuation information after passing through the human body through the detector; S13: Convert the received attenuation information into a two-dimensional tomographic image through the reconstruction algorithm in the CT device. The reconstruction algorithm uses the filtered back-projection technique, and the specific formula is: , where represents the reconstructed two-dimensional tomographic image, and are the coordinate positions of the image; represents the projection angle and the projection distance at which the projection data is received; represents the projection angle; represents the projection path distance; represents the convolution kernel of the filtering function acting on the projection data, where is the projection path coordinate; and are the cosine and sine functions of the projection angle respectively; is the integration variable, representing the accumulated weight of the image points along different projection angles .

3. The method for enhancing CT image quality and reducing noise assisted by artificial intelligence according to claim 1, characterized in that, The specific content of S2 includes: S21: Perform normalization processing on the obtained low-dose CT image data, adjust the gray-scale values of the image data to a predetermined range, so that the gray-scale values of all pixels are between 0 and 1; S22: Perform artifact removal processing on the normalized image, based on the bilateral filtering algorithm, through joint smoothing processing of the space and pixel intensity of the image; S23: Perform edge smoothing processing on the image after artifact removal, and remove high-frequency noise in the image by applying Gaussian smoothing filtering technology.

4. The method for enhancing CT image quality and reducing noise assisted by artificial intelligence according to claim 1, characterized in that, The specific content of S3 includes: S31: Extract edge features from the preprocessed image data, specifically using a gradient-based edge detection algorithm, and identify the regions where the gray-scale values of the pixels in the image change sharply by calculating the change rate of the gray-scale values of the pixels in the image; S32: Extract texture features from the image after edge feature extraction, use the gray-level co-occurrence matrix analysis method, and extract local texture information in the image by statistically analyzing the co-occurrence relationship of adjacent pixel gray-scale values, including the directionality, roughness, and repeatability of the texture; S33: While extracting texture features, extract the gray-scale distribution features of the image, calculate the overall gray-scale value distribution of the image, and obtain the distribution of bright and dark regions in the image by statistically analyzing the gray-scale histogram of pixels.

5. The method for enhancing CT image quality and reducing noise assisted by artificial intelligence according to claim 1, wherein The specific steps of S4 are as follows: S41: Input the extracted preliminary feature information into a pre-trained convolutional neural network model, which consists of multiple convolutional layers, pooling layers, and fully connected layers, and extract image features at different scales through convolutional operations. S42: In the convolutional layer, the convolutional kernel scans the input image features pixel by pixel and calculates the feature responses of local regions. S43: In the pooling layer, reduce the data dimension through downsampling operations, extract the image features, and at the same time retain the key noise patterns of the image. S44: After multiple convolutional and pooling processes, enter the fully connected layer to calculate the feature weights. Through adaptive learning of the feature weights, generate a feature weight matrix related to noise, which is used to reflect the intensity, distribution, and position of noise in the image. S45: Finally, by outputting the feature weight matrix, the convolutional neural network can adaptively estimate the noise in the image and generate a corresponding noise distribution model.

6. The method for enhancing CT image quality and reducing noise assisted by artificial intelligence according to claim 5, wherein The specific steps of S5 are as follows: S51: Use the noise estimation result and the preliminary feature information as inputs and input them into a deep convolutional denoising network. The preliminary feature information includes the edges, textures, and gray-scale distributions of the image, while the noise estimation result represents the noise distribution at each pixel position in the image. S52: In the deep convolutional denoising network, use multiple convolutional operations to jointly process the noise estimation result and the preliminary feature information. The joint processing synthesizes the noise and feature information in the image through convolutional operations, enabling the denoising process to consider the structural features of the image and extract the joint distribution of noise and features. S53: Perform deconvolution operations on the image features after convolutional processing to map the extracted high-dimensional features back to the spatial dimension of the original image and generate a denoised image. S54: Perform weight fusion on the denoised image obtained by deconvolution and the preliminary feature information, and balance the denoising effect and the retention of image detail features by adjusting the weight ratio, thereby generating the final denoised image.

7. The method for enhancing CT image quality and reducing noise assisted by artificial intelligence according to claim 1, wherein, The specific steps of S6 are as follows: S61: Input the denoised CT image into the generator in the generative adversarial network framework. The generator is a convolutional neural network structure, which extracts and enhances the detail features in the input denoised image through convolutional and deconvolution operations. S62: The generator extracts the feature information in the denoised image through multiple convolutional layers and gradually adjusts the details in the image. S63: Input the generated enhanced CT image into the discriminator. The discriminator compares the enhanced image with a preset standard image, calculates the difference between the two, and outputs a similarity score. S64: Based on the feedback of the discriminator, the generator will optimize the image generation process. By continuously adjusting the weights of the convolutional kernels, maximize the similarity between the enhanced image and the standard image. Thus, the training of the generative adversarial network is optimized through multiple iterations, and the output gradually approaches the quality of the standard high-dose CT image.

8. The method for enhancing CT image quality and reducing noise assisted by artificial intelligence according to claim 7, wherein The specific steps of S63 are as follows: S631: Take the generated enhanced CT image and the preset standard high-dose CT image as inputs, and send them into the convolutional neural network structure of the discriminator respectively. Through convolutional operations, extract the feature vectors of the enhanced image and the standard image respectively; S632: The discriminator compares the feature vectors of the enhanced image and the standard image, calculates the difference between them, and obtains the overall difference value of the two images in the feature space by comparing the feature differences of each pixel point; S633: According to the calculated difference value, calculate the similarity score. The similarity score represents the matching degree between the enhanced image and the standard image. The higher the score, the closer they are in details and structure.

9. The method for enhancing CT image quality and reducing noise assisted by artificial intelligence according to claim 1, characterized in that The specific steps of S7 are as follows: S71: Take the quality-enhanced CT image as input, send it into the image reconstruction module, and reconstruct the image through the filtered back-projection technique; S72: During the reconstruction process, use the high signal-to-noise ratio optimization algorithm to optimize the reconstructed image; S73: Use the structure fidelity optimization algorithm to ensure the detail and structure fidelity of the reconstructed image. Specifically, optimize the image quality by calculating the structural similarity index of the image.

10. The method for enhancing CT image quality and reducing noise assisted by artificial intelligence according to claim 1, wherein The specific steps of S8 are as follows: S81: Input the finally reconstructed CT image into the trained medical image discrimination model; S82: The discrimination model extracts the features of the input CT image through multiple convolutional layers and pooling layers, and extracts the structural information, texture features and gray-scale distribution in the image; S83: The discrimination model inputs the extracted image features into the preset classification algorithm through the classification layer to evaluate the diagnostic applicability of the image; S84: According to the classification result, the discrimination model outputs a medical applicability score, and the score range is from 0 to 1, which is used to reflect whether the image is suitable for clinical diagnosis. If the score reaches the preset threshold, it indicates that the CT image meets the clinical diagnosis requirements.

Images