Pulmonary nodule segmentation method and device based on ABVM-UNet

Abstract

The invention provides a pulmonary nodule segmentation method and device based on ABVM-UNet, and the method comprises the steps: S1, collecting a lung CT image data set, carrying out the enhancement processing of a pulmonary nodule region in an image, and highlighting the texture and edge features of a nodule; s2, constructing a main branch and a target enhancement auxiliary branch based on a Gabor convolutional neural network to realize enhancement response to pulmonary nodule texture and edge features; s3, using a branch information interaction fusion module BIIF to realize fusion and transmission of auxiliary branch enhancement features; s4, constructing a U-shaped architecture network ABVM-UNet based on Vision Mama, and realizing effective fusion of the local features of the image and the global context information; s5, multi-stage segmentation loss is realized by using depth supervision, and the ABVM-UNet model is trained and optimized; and S6, carrying out pulmonary nodule segmentation on the lung CT image by using an ABVM-UNet model. According to the method, the edge and texture features of the pulmonary nodule are effectively extracted by introducing the ABVM-UNet model, so that accurate segmentation of the pulmonary nodule is realized.

Description

Technical Field

[0001] The present invention relates to the field of medical imaging, and in particular to a pulmonary nodule segmentation method and device based on ABVM-UNet. Background Art

[0002] According to statistics from the World Health Organization's International Agency for Research on Cancer, lung cancer ranks first in cancer incidence and has the highest mortality rate in the world. Early detection of lung nodules is extremely important for the prevention and treatment of lung cancer. During the screening process, doctors need to accurately mark the lesions in CT images and use lung nodule segmentation algorithms to define the edges of nodules in order to monitor their growth and morphological changes, and measure key data such as nodule size and diameter.

[0003] In recent years, deep learning technology has become a hot topic in the field of pulmonary nodule segmentation, and many deep learning-based methods have been proposed and applied to this task. These models can automatically learn and extract features from CT slices to achieve pulmonary nodule segmentation. Although these deep learning models have made significant progress in pulmonary nodule segmentation, they still have certain limitations when dealing with fuzzy nodule edges and complex texture features. For example, when the boundary between the nodule and the surrounding lung tissue is unclear or the internal structure of the nodule is similar to that of normal lung tissue, the model often finds it difficult to accurately distinguish the nodule from its surrounding tissue. This not only affects the accuracy of the nodule edge definition, but may also lead to false positive or false negative results, thereby affecting subsequent diagnosis and treatment decisions. Therefore, how to effectively capture and utilize the subtle features of the texture and edges of pulmonary nodules to improve the segmentation accuracy of the model has become a key issue that needs to be solved in current research. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides a lung nodule segmentation method and device based on ABVM-UNet, which can realize accurate segmentation of lung nodules in lung CT images for users.

[0005] Specifically, the method comprises the following steps:

[0006] S1: Collect lung CT image datasets, enhance the lung nodule area in the image, and highlight the texture and edge features of the nodules;

[0007] S2: Construct the main branch and the target enhancement auxiliary branch based on Gabor convolutional neural network to achieve enhanced response to the texture and edge features of lung nodules;

[0008] S3: Use the branch information interaction fusion module BIIF to achieve the fusion and transmission of auxiliary branch enhancement features;

[0009] S4: Build a U-shaped network ABVM-UNet based on Vision Mamba to achieve effective fusion of local image features and global context information;

[0010] S5: Implementing multi-level segmentation loss using deep supervision and training and optimizing the ABVM-UNet model;

[0011] S6: Use the ABVM-UNet model to segment lung nodules in lung CT images.

[0012] Preferably, S1 comprises the following steps:

[0013] S1.1: Collect lung CT image datasets, generate lung parenchyma images and unify the pixel intervals between images;

[0014] Preferably, S1.1 comprises the following steps:

[0015] S1.1.1: Collect a lung CT image dataset, multiply the image by the lung mask image element by element, remove irrelevant areas, and generate a lung parenchyma image;

[0016] S1.1.2: Resample the lung parenchymal images to uniform pixel spacing.

[0017] S1.2: intercepting a lung nodule image block, and performing an image enhancement operation on the lung nodule tissue portion in the image block to obtain an enhanced image block;

[0018] Preferably, S1.2 comprises the following steps:

[0019] S1.2.1: Taking the central coordinate point of the lung nodule as the center, cut out image blocks of the same size from the lung parenchyma image and the lung nodule mask image, and record them as Image raw and GroundTruth;

[0020] S1.2.2: Multiply the original image block and the lung nodule mask image block element by element, retain only the information of the lung nodule tissue, perform SG double filtering at the same time, and superimpose the image block after the filtering operation into the original image block as the enhanced image block Image aug .

[0021] S1.3: Perform data preprocessing operations on the original image block and the enhanced image block, and perform image data augmentation operations at the same time.

[0022] Among them, S1.3 includes the following steps:

[0023] S1.3.1: Perform data normalization and de-averaging on the original image block and the enhanced image block;

[0024] S1.3.2: Augment data using image data augmentation techniques.

[0025] Preferably, S2 comprises the following steps:

[0026] S2.1: Construct the main branch and the target enhancement auxiliary branch based on Gabor convolutional neural network. The main branch is composed of multiple Conv modules, and the target enhancement auxiliary branch is composed of multiple GCN modules.

[0027] S2.2: The original image block Image raw Input the main branch Conv module to perform feature extraction calculation and obtain the feature map f main ;

[0028] Preferably, S2.2 comprises the following steps:

[0029] Using convolutional neural network, convolution calculation is performed to obtain the Conv structure:

[0030] f maim =Swish(BN(conv(x)))

[0031] In the above formula, Swish(.) represents the Swish activation function, BN(.) represents Batch Normalization, conv(.) represents the convolution kernel, and x represents the input data.

[0032] S2.3: Enhance the image block Image aug Input the target enhancement auxiliary branch GCN module to perform feature extraction calculation and obtain the enhanced feature map f aug .

[0033] Preferably, S2.3 comprises the following steps:

[0034] Using Gabor convolutional neural network, convolution calculation is performed to obtain the GCN structure:

[0035] f aug =Swish(BN(Gabor(x)))

[0036] In the above formula, Swish(.) represents the Swish activation function, BN(.) represents Batch Normalization, Gabor(.) represents Gabor filtering, and x represents the input data.

[0037] Preferably, S3 comprises the following steps:

[0038] S3.1: Construct the branch information interaction fusion module BIIF (Branch Information Interaction Fusion);

[0039] S3.2: The feature f extracted by the main branch main The feature f extracted by the target enhancement auxiliary branch aug Input the BIIF module to perform information interaction and fusion to obtain the fused feature f m ′ ain With f a ′ ug .

[0040] Preferably, S3.2 comprises the following steps:

[0041] Different calculation methods are used for the features extracted by the main branch and the target enhanced auxiliary branch to obtain the BIIF structure:

[0042] f′ main =f main

[0043] +Res(channelshuffle(concatenate(VSS(f main )

[0044] +VSS(f aug ))))

[0045] f′ aug =f aug

[0046] +Res(channelshuffle(concatenate(VSS(f main )

[0047] +VSS(f aug ))))

[0048] In the above formula, f main represents the features extracted by the main branch, f aug Represents the features extracted by the target enhancement auxiliary branch, Res(.) represents the residual module, channel shuffle(.) represents the channel shuffle operation, that is, rearranging the channel order of the original feature map to enhance the interactive fusion of information between channels, concatenate(.) represents the channel dimension concatenation operation, and VSS(.) represents the VSS module based on Vision Mamba.

[0049] Preferably, S4 comprises the following steps:

[0050] S4.1: Design a U-shaped network ABVM-UNet based on Vision Mamba;

[0051] S4.2: Effectively integrate the Conv module, GCN module, BIIF module and VSS module into ABVM-UNet to achieve effective fusion of local image features and global context information.

[0052] Preferably, S4.2 comprises the following steps:

[0053] S4.2.1: The encoder of ABVM-UNet consists of a main branch and a target-enhanced auxiliary branch, which is composed of multiple Conv modules, GCN modules, and BIIF modules alternating with each other;

[0054] S4.2.2: The bottleneck of ABVM-UNet is the part where the encoder is converted to a decoder, which consists of two VSS modules;

[0055] S4.2.3: The decoder of ABVM-UNet consists of multiple Conv modules and VSS modules alternating with each other, and a 1*1 convolutional layer is used in the last layer of the decoder to predict the segmentation result;

[0056] S4.2.4: The downsampling part between each encoder layer of ABVM-UNet uses the Max Pooling operation, and the upsampling part between each decoder layer uses the deconvolution operation;

[0057] S4.2.5: ABVM-UNet uses skip connections to concatenate the output of the BIIF module in the encoder with the output of the VSS module in the decoder in the channel dimension, and performs channel shuffling operations at the same time.

[0058] Preferably, S5 comprises the following steps:

[0059] S5.1: The segmentation loss is calculated for the segmentation prediction results of each layer of the model decoder through deep supervision. The segmentation loss consists of Dice loss and Binary Cross-Entropy loss.

[0060] Preferably, S5.1 comprises the following steps:

[0061] S5.1.1: Use a 1*1 convolution operation for each decoder layer to obtain multi-scale segmentation prediction results. From the shallow layer to the deep layer of the decoder, the segmentation prediction results are recorded as: Pred, Pred1, Pred2, Pred3, Pred4;

[0062] S5.1.2: Calculate the segmentation loss based on the pulmonary nodule mask label and the segmentation prediction result Pred;

[0063] S5.1.3: Perform Bilinear Interpolation upsampling on Pred1 and Pred2 to obtain the segmentation prediction result of the same size as the pulmonary nodule mask label, and calculate its segmentation loss;

[0064] S5.1.4: Perform Max Pooling downsampling on the lung nodule mask labels to obtain lung nodule mask labels of the same size as Pred3 and Pred4, and calculate the segmentation loss of the segmentation prediction results Pred3 and Pred4.

[0065] S5.2: Assign a weight parameter to the segmentation loss of each layer of the decoder and form a multi-level segmentation loss;

[0066] Preferably, S5.2 comprises the following steps:

[0067] Using Dice loss and cross entropy loss, the loss of the segmentation prediction results of each layer of decoder is calculated to obtain the multi-level segmentation loss:

[0068]

[0069] In the above formula, L seg Represents the segmentation loss of the segmentation prediction result, L Dice (.) represents Dice loss, L BCE (.) represents Binary Cross-Entropy cross entropy loss, y represents the pulmonary nodule mask label, Represents the final segmentation prediction result, represents the segmentation prediction result of the i-th layer decoder, L i represents the segmentation loss of the i-th layer decoder segmentation prediction result, BI(.) represents Bilinear Interpolation upsampling, MP(.) represents Max Pooling downsampling, L total represents the multi-level segmentation loss, α i Represents the weight parameter of the segmentation loss of the i-th layer decoder.

[0070] S5.3: Use multi-level segmentation loss to train and optimize the ABVM-UNet model. During the training process, the back propagation algorithm is used to optimize the model parameters to reduce the multi-level segmentation loss and thus improve the segmentation performance of the model.

[0071] Preferably, S6 comprises the following steps:

[0072] S6.1: Import the pre-trained weights of the ABVM-UNet model and use the model to segment lung nodules in lung CT images;

[0073] S6.2: Superimpose the segmentation prediction result on the lung CT image, and mark the predicted lung nodule tissue location to obtain the lung nodule segmentation result of the patient's CT image.

[0074] The second technical solution adopted by the present invention is: a pulmonary nodule segmentation device based on ABVM-UNet, comprising:

[0075] Preprocessing module: used to collect data, perform a series of preprocessing and SG double filtering operations on the data, and convert it into the input format of the model;

[0076] GCN module: used for target enhancement auxiliary branch to realize the model's enhanced response to the texture and edge features of lung nodules;

[0077] Conv module: used for the main branch to realize the effective extraction of lung nodule features by the model;

[0078] VSS module: used to model the remote interaction of data and effectively extract the global context information of the image;

[0079] BIIF module: used to fuse the features extracted by the main branch and the target enhanced auxiliary branch, and realize the fusion and transmission of the enhanced features of the auxiliary branch;

[0080] Multi-level segmentation loss module: used to train and optimize the model to minimize the prediction error and improve the performance of the model.

[0081] The beneficial effects of the method and device of the present invention are as follows: the present invention first obtains an enhanced image of the lung nodule target by performing a series of preprocessing and SG double filtering operations on the lung CT image. Next, the main branch and the target enhancement auxiliary branch are designed to realize the model's effective extraction of image features and enhanced response to the texture and edge features of the lung nodules. Then, the branch information interactive fusion module realizes the effective fusion of the features extracted by the main branch and the target enhancement auxiliary branch. Finally, the various modules are integrated through the U-shaped network architecture ABVM-UNet based on Vision Mamba to realize the effective fusion of local image features and global contextual information, so as to achieve the purpose of accurately segmenting lung nodule tissue in lung CT images. At the same time, the present invention can significantly overcome the challenges commonly faced by existing deep learning models in the field of lung nodule segmentation. On the one hand, by adopting a dual-branch network structure, the model's ability to extract lung nodule features in CT images is effectively enhanced, and the feature representation is enriched; on the other hand, with the help of the branch information interaction fusion module, the model's ability to efficiently integrate features at each stage is enhanced; at the same time, through the lung nodule segmentation model based on ABVM-UNet, the model's accurate capture and effective fusion of local image features and global contextual information are improved, ultimately improving the accuracy of lung nodule segmentation in lung CT images. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the prior art and the drawings required for use in the embodiments. The following drawings are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0083] Figure 1 It is a flowchart of a lung nodule segmentation method based on ABVM-UNet of the present invention;

[0084] Figure 2 This is a model architecture diagram of a lung nodule segmentation method based on ABVM-UNet of the present invention;

[0085] Figure 3 It is a schematic diagram of the BIIF module structure of a lung nodule segmentation method based on ABVM-UNet of the present invention. Specific implementation plan

[0086] In order to make the purpose, features and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all other embodiments obtained by ordinary technicians in this field without creative work based on the embodiments of the present invention are within the scope of protection of the present invention.

[0087] The embodiments of the present application provide a lung nodule segmentation method and device based on ABVM-UNet, which are used to effectively extract lung nodule feature information from lung CT images, thereby achieving accurate segmentation of lung nodules.

[0088] As a typical embodiment of the present invention, the LUNA16 lung nodule dataset is taken as an example. Figure 1 As shown, the method comprises the following steps:

[0089] S1: Collect lung CT image datasets, enhance the lung nodule area in the image, and highlight the texture and edge features of the nodules;

[0090] S2: Construct the main branch and the target enhancement auxiliary branch based on Gabor convolutional neural network to achieve enhanced response to the texture and edge features of lung nodules;

[0091] S3: Use the branch information interaction fusion module BIIF to achieve the fusion and transmission of auxiliary branch enhancement features;

[0092] S4: Build a U-shaped network ABVM-UNet based on Vision Mamba to achieve effective fusion of local image features and global context information;

[0093] S5: Implementing multi-level segmentation loss using deep supervision and training and optimizing the ABVM-UNet model;

[0094] S6: Use the ABVM-UNet model to segment lung nodules in lung CT images.

[0095] Further, S1 comprises the following steps:

[0096] S1.1: Collect lung CT image datasets, generate lung parenchyma images and unify the pixel intervals between images;

[0097] Further, S1.1 includes the following steps:

[0098] S1.1.1: Collect a lung CT image dataset, multiply the image by the lung mask image element by element, remove irrelevant areas, and generate a lung parenchyma image;

[0099] S1.1.2: Resample the lung parenchymal images to uniform pixel spacing.

[0100] S1.2: intercepting a lung nodule image block, and performing an image enhancement operation on the lung nodule tissue portion in the image block to obtain an enhanced image block;

[0101] Further, S1.2 includes the following steps:

[0102] S1.2.1: Taking the central coordinate point of the lung nodule as the center, cut out image blocks of the same size from the lung parenchyma image and the lung nodule mask image, and record them as Image raw and GroundTruth;

[0103] S1.2.2: Multiply the original image block and the lung nodule mask image block element by element, retaining only the information of the lung nodule tissue, and use the Sobel filter and Gabor filter to perform SG double filtering on the image, and superimpose the image block after the filtering operation into the original image block as the enhanced image block Image aug .

[0104] S1.3: Perform data preprocessing operations on the original image block and the enhanced image block, and perform image data augmentation operations at the same time.

[0105] Further, S1.3 includes the following steps:

[0106] S1.3.1: Perform data normalization and de-averaging on the original image block and the enhanced image block;

[0107] S1.3.2: Augment the image data by using image rotation, image scaling, vertical symmetrical flipping, horizontal symmetrical flipping, and color dithering.

[0108] Further, refer to Figure 2 , S2 includes the following steps:

[0109] S2.1: Construct the main branch and the target enhancement auxiliary branch based on Gabor convolutional neural network. The main branch is composed of multiple Conv modules, and the target enhancement auxiliary branch is composed of multiple GCN modules.

[0110] S2.2: The original image block Image raw Input the main branch Conv module to perform feature extraction calculation and obtain the feature map f main ;

[0111] Further, S2.2 includes the following steps:

[0112] Using convolutional neural network, convolution calculation is performed to obtain the Conv structure:

[0113] f main =Swish(BN(conv(x)))

[0114] In the above formula, Swish(.) represents the Swish activation function, BN(.) represents Batch Normalization, conv(.) represents the convolution kernel, and x represents the input data.

[0115] S2.3: Enhance the image block Image aug Input the target enhancement auxiliary branch GCN module to perform feature extraction calculation and obtain the enhanced feature map f aug .

[0116] Further, S2.3 includes the following steps:

[0117] Using Gabor convolutional neural network, convolution calculation is performed to obtain the GCN structure:

[0118] f aug =Swish(BN(Gabor(x)))

[0119] In the above formula, Swish(.) represents the Swish activation function, BN(.) represents Batch Normalization, Gabor(.) represents Gabor filtering, and x represents the input data.

[0120] Further, refer to Figure 3 , S3 includes the following steps:

[0121] S3.1: Construct the branch information interaction fusion module BIIF (Branch Information Interaction Fusion);

[0122] S3.2: The feature f extracted by the main branch main The feature f extracted by the target enhancement auxiliary branch aug Input the BIIF module to perform information interaction and fusion to obtain the fused feature f′ main and f′ aug .

[0123] Further, S3.2 includes the following steps:

[0124] Different calculation methods are used for the features extracted by the main branch and the target enhanced auxiliary branch to obtain the BIIF structure:

[0125] f′ main =f main

[0126] +Res(channelshuffle(concatenate(VSS(f main )

[0127] +VSS(f aug ))))

[0128] f′ aug =f aug

[0129] +Res(channelshuffle(concatenate(VSS(f main )

[0130] +VSS(f aug ))))

[0131] In the above formula, f main represents the features extracted by the main branch, f aug Represents the features extracted by the target enhancement auxiliary branch, Res(.) represents the residual module, channelshuffle(.) represents the channel shuffle operation, that is, rearranging the channel order of the original feature map to enhance the interactive fusion of information between channels, concatenate(.) represents the channel dimension concatenation operation, and VSS(.) represents the VSS module based on Vision Mamba.

[0132] Further, refer to Figure 2 , S4 comprises the following steps:

[0133] S4.1: Design a U-shaped network ABVM-UNet based on Vision Mamba;

[0134] S4.2: Effectively integrate the Conv module, GCN module, BIIF module and VSS module into ABVM-UNet to achieve effective fusion of local image features and global context information.

[0135] Further, S4.2 includes the following steps:

[0136] S4.2.1: The encoder of ABVM-UNet consists of a main branch and a target-enhanced auxiliary branch, which is composed of multiple Conv modules, GCN modules, and BIIF modules alternating with each other;

[0137] S4.2.2: The bottleneck of ABVM-UNet is the part where the encoder is converted to a decoder, which consists of two VSS modules;

[0138] S4.2.3: The decoder of ABVM-UNet consists of multiple Conv modules and VSS modules alternating with each other, and a 1*1 convolutional layer is used in the last layer of the decoder to predict the segmentation result;

[0139] S4.2.4: The downsampling part between each encoder layer of ABVM-UNet uses the Max Pooling operation, and the upsampling part between each decoder layer uses the deconvolution operation;

[0140] S4.2.5: ABVM-UNet uses skip connections to concatenate the output of the BIIF module in the encoder with the output of the VSS module in the decoder in the channel dimension, and performs channel shuffling operations at the same time.

[0141] Further, refer to Figure 2 , S5 comprises the following steps:

[0142] S5.1: The segmentation loss is calculated for the segmentation prediction results of each layer of the model decoder through deep supervision. The segmentation loss consists of Dice loss and Binary Cross-Entropy loss.

[0143] Further, S5.1 includes the following steps:

[0144] S5.1.1: Use a 1*1 convolution operation for each decoder layer to obtain multi-scale segmentation prediction results. From the shallow layer to the deep layer of the decoder, the segmentation prediction results are recorded as: Pred, Pred1, Pred2, Pred3, Pred4;

[0145] S5.1.2: Calculate the segmentation loss based on the pulmonary nodule mask label and the segmentation prediction result Pred;

[0146] S5.1.3: Perform Bilinear Interpolation upsampling on Pred1 and Pred2 to obtain the segmentation prediction result of the same size as the pulmonary nodule mask label, and calculate its segmentation loss;

[0147] S5.1.4: Perform Max Pooling downsampling on the lung nodule mask labels to obtain lung nodule mask labels of the same size as Pred3 and Pred4, and calculate the segmentation loss of the segmentation prediction results Pred3 and Pred4.

[0148] S5.2: Assign a weight parameter to the segmentation loss of each layer of the decoder and form a multi-level segmentation loss;

[0149] Further, S5.2 comprises the following steps:

[0150] Using Dice loss and cross entropy loss, the loss of the segmentation prediction results of each layer of decoder is calculated to obtain the multi-level segmentation loss:

[0151]

[0152] In the above formula, L seg Represents the segmentation loss of the segmentation prediction result, L Dice (.) represents Dice loss, L BCE (.) represents Binary Cross-Entropy cross entropy loss, y represents the pulmonary nodule mask label, Represents the final segmentation prediction result, represents the segmentation prediction result of the i-th layer decoder, L i represents the segmentation loss of the i-th layer decoder segmentation prediction result, BI(.) represents Bilinear Interpolation upsampling, MP(.) represents Max Pooling downsampling, L total represents the multi-level segmentation loss, α i Represents the weight parameter of the segmentation loss of the i-th layer decoder.

[0153] S5.3: Use multi-level segmentation loss to train and optimize the ABVM-UNet model. During the training process, the back propagation algorithm is used to optimize the model parameters to reduce the multi-level segmentation loss and thus improve the segmentation performance of the model.

[0154] Further, S6 comprises the following steps:

[0155] S6.1: Import the pre-trained weights of the ABVM-UNet model and use the model to segment lung nodules in lung CT images;

[0156] S6.2: Superimpose the segmentation prediction result on the lung CT image, and mark the predicted lung nodule tissue location to obtain the lung nodule segmentation result of the patient's CT image.

[0157] The above is a specific description of the implementation of the present invention, but the invention is not limited to the embodiments. Technical personnel should know that although the present invention has been described according to the above specific implementation methods, the inventive concept of the present invention is not limited to this invention. Any modification using the inventive concept will be included in the scope of protection of this patent.

Claims

1. A pulmonary nodule segmentation method based on ABVM-UNet, characterized in that: The method comprises the following steps: S1: Collect lung CT image datasets, enhance the lung nodule area in the image, and highlight the texture and edge features of the nodules; S2: Construct the main branch and the target enhancement auxiliary branch based on Gabor convolutional neural network to achieve enhanced response to the texture and edge features of lung nodules; S3: Use the branch information interaction fusion module BIIF to achieve the fusion and transmission of auxiliary branch enhancement features; S4: Build a U-shaped network ABVM-UNet based on Vision Mamba to achieve effective fusion of local image features and global context information; S5: Implementing multi-level segmentation loss using deep supervision and training and optimizing the ABVM-UNet model; S6: Use the ABVM-UNet model to segment lung nodules in lung CT images.

2. The pulmonary nodule segmentation method based on ABVM-UNet according to claim 1, characterized in that: S1 includes the following steps: S1.1: Collect lung CT image datasets, generate lung parenchyma images and unify the pixel intervals between images; Among them, S1.1 includes the following steps: S1.1.1: Collect a lung CT image dataset, multiply the image by the lung mask image element by element, remove irrelevant areas, and generate a lung parenchyma image; S1.1.2: Resample the lung parenchymal images to uniform pixel spacing. S1.2: intercepting a lung nodule image block, and performing an image enhancement operation on the lung nodule tissue portion in the image block to obtain an enhanced image block; Among them, S1.2 includes the following steps: S1.2.1: Taking the central coordinate point of the lung nodule as the center, cut out image blocks of the same size from the lung parenchyma image and the lung nodule mask image, and record them as Image raw and GroundTruth; S1.2.2: Multiply the original image block and the lung nodule mask image block element by element, retain only the information of the lung nodule tissue, perform SG double filtering at the same time, and superimpose the image block after the filtering operation into the original image block as the enhanced image block Image aug . S1.3: Perform data preprocessing operations on the original image block and the enhanced image block, and perform image data augmentation operations at the same time. Among them, S1.3 includes the following steps: S1.3.1: Perform data normalization and de-averaging on the original image block and the enhanced image block; S1.3.2: Augment data using image data augmentation techniques.

3. The pulmonary nodule segmentation method based on ABVM-UNet according to claim 1, characterized in that: S2 includes the following steps: S2.1: Construct the main branch and the target enhancement auxiliary branch based on Gabor convolutional neural network. The main branch is composed of multiple Conv modules, and the target enhancement auxiliary branch is composed of multiple GCN modules. S2.2: The original image block Image raw Input the main branch Conv module to perform feature extraction calculation and obtain the feature map f main ; Among them, S2.2 includes the following steps: Using convolutional neural network, convolution calculation is performed to obtain the Conv structure: f main =Swish(BN(conv(x))) In the above formula, Swish(.) represents the Swish activation function, BN(.) represents Batch Normalization, conv(.) represents the convolution kernel, and x represents the input data. S2.3: Enhance the image block Image aug Input the target enhancement auxiliary branch GCN module to perform feature extraction calculation and obtain the enhanced feature map f aug . Among them, S2.3 includes the following steps: Using Gabor convolutional neural network, convolution calculation is performed to obtain the GCN structure: f aug =Swish(BN(Gabor(x))) In the above formula, Swish(.) represents the Swish activation function, BN(.) represents Batch Normalization, Gabor(.) represents Gabor filtering, and x represents the input data.

4. The pulmonary nodule segmentation method based on ABVM-UNet according to claim 1, characterized in that: S3 includes the following steps: S3.1: Construct the branch information interaction fusion module BIIF (Branch Information Interaction Fusion); S3.2: The feature f extracted by the main branch main The feature f extracted by the target enhancement auxiliary branch aug Input the BIIF module to perform information interaction and fusion to obtain the fused feature f′ main and f′ aug . Among them, S3.2 includes the following steps: Different calculation methods are used for the features extracted by the main branch and the target enhanced auxiliary branch to obtain the BIIF structure: f′ main =f main +Res(channelshuffle(concatenate(VSS(f main )+VSS(f aug )))) f′ aug =f aug +Res(channelshuffle(concatenate(VSS(f main )+VSS(f aug )))) In the above formula, f main represents the features extracted by the main branch, f aug Represents the features extracted by the target enhancement auxiliary branch, Res(.) represents the residual module, channelshuffle(.) represents the channel shuffle operation, that is, rearranging the channel order of the original feature map to enhance the interactive fusion of information between channels, concatenate(.) represents the channel dimension concatenation operation, and VSS(.) represents the VSS module based on Vision Mamba.

5. The pulmonary nodule segmentation method based on ABVM-UNet according to claim 1, characterized in that: S4 includes the following steps: S4.1: Design a U-shaped architecture network ABVM-UNet based on Vision Mamba; S4.2: Effectively integrate the Conv module, GCN module, BIIF module and VSS module into ABVM-UNet to achieve effective fusion of local image features and global context information. Among them, S4.2 includes the following steps: S4.2.1: The encoder of ABVM-UNet consists of a main branch and a target-enhanced auxiliary branch, which is composed of multiple Conv modules, GCN modules, and BIIF modules alternating with each other; S4.2.2: The bottleneck of ABVM-UNet is the part where the encoder is converted to a decoder, which consists of two VSS modules; S4.2.3: The decoder of ABVM-UNet consists of multiple Conv modules and VSS modules alternating with each other, and a 1*1 convolutional layer is used in the last layer of the decoder to predict the segmentation result; S4.2.4: The downsampling part between each encoder layer of ABVM-UNet uses the Max Pooling operation, and the upsampling part between each decoder layer uses the deconvolution operation; S4.2.5: ABVM-UNet uses skip connections to concatenate the output of the BIIF module in the encoder with the output of the VSS module in the decoder in the channel dimension, and performs channel shuffling operations at the same time.

6. The pulmonary nodule segmentation method based on ABVM-UNet according to claim 1, characterized in that: S5 includes the following steps: S5.1: The segmentation loss is calculated for the segmentation prediction results of each layer of the model decoder through deep supervision. The segmentation loss consists of Dice loss and Binary Cross-Entropy loss. Among them, S5.1 includes the following steps: S5.1.1: Use a 1*1 convolution operation for each decoder layer to obtain multi-scale segmentation prediction results. From the shallow layer to the deep layer of the decoder, the segmentation prediction results are recorded as: Pred, Pred1, Pred2, Pred3, Pred4; S5.1.2: Calculate the segmentation loss based on the pulmonary nodule mask label and the segmentation prediction result Pred; S5.1.3: Perform Bilinear Interpolation upsampling on Pred1 and Pred2 to obtain the segmentation prediction result of the same size as the pulmonary nodule mask label, and calculate its segmentation loss; S5.1.4: Perform Max Pooling downsampling on the lung nodule mask labels to obtain lung nodule mask labels of the same size as Pred3 and Pred4, and calculate the segmentation loss of the segmentation prediction results Pred3 and Pred4. S5.2: Assign a weight parameter to the segmentation loss of each layer of the decoder and form a multi-level segmentation loss; Among them, S5.2 includes the following steps: Using Dice loss and cross entropy loss, the loss of the segmentation prediction results of each layer of decoder is calculated to obtain the multi-level segmentation loss: In the above formula, L seg Represents the segmentation loss of the segmentation prediction result, L Dice (.) represents Dice loss, L BCE (.) represents BinaryCross-Entropy cross entropy loss, y represents the pulmonary nodule mask label, Represents the final segmentation prediction result, represents the segmentation prediction result of the i-th layer decoder, L i represents the segmentation loss of the i-th layer decoder segmentation prediction result, BI(.) represents Bilinear Interpolation upsampling, MP(.) represents Max Pooling downsampling, L total represents the multi-level segmentation loss, α i Represents the weight parameter of the segmentation loss of the i-th layer decoder. S5.3: Use multi-level segmentation loss to train and optimize the ABVM-UNet model. During the training process, the back propagation algorithm is used to optimize the model parameters to reduce the multi-level segmentation loss and thus improve the segmentation performance of the model.

7. The pulmonary nodule segmentation method based on ABVM-UNet according to claim 1, characterized in that: S6 includes the following steps: S6.1: Import the pre-trained weights of the ABVM-UNet model and use the model to segment lung nodules in lung CT images; S6.2: Superimpose the segmentation prediction result on the lung CT image, and mark the predicted lung nodule tissue location to obtain the lung nodule segmentation result of the patient's CT image.

8. A pulmonary nodule segmentation device based on ABVM-UNet, characterized in that: include: Preprocessing module: used to collect data, perform a series of preprocessing and SG double filtering operations on the data, and convert it into the input format of the model; GCN module: used for target enhancement auxiliary branch to realize the model's enhanced response to the texture and edge features of lung nodules; Conv module: used for the main branch to realize the effective extraction of lung nodule features by the model; VSS module: used to model the remote interaction of data and effectively extract the global context information of the image; BIIF module: used to fuse the features extracted by the main branch and the target enhanced auxiliary branch, and realize the fusion and transmission of the enhanced features of the auxiliary branch; Multi-level segmentation loss module: used to train and optimize the model to minimize the prediction error and improve the performance of the model.

Images