CN117078941B - Cardiac MRI segmentation method based on context cascade attention - Google Patents

Abstract

A cardiac MRI segmentation method based on context cascade attention, involving the field of medical image segmentation technology, introduces a residual initial module in the encoder to better learn effective feature representation and improve the performance and generalization ability of the model. The complementary information of different layers is utilized in the decoder through cascade operations to refine the features of each layer, while the contextual attention module is used to explore the contextual information of each layer by retaining local information and compressing global information, and suppressing unimportant information area to highlight salient features, thereby improving the accuracy of segmentation.

Description

A cardiac MRI segmentation method based on context cascade attention

Technical field

The invention relates to the technical field of medical image segmentation, and in particular to a cardiac MRI segmentation method based on context cascade attention.

Background technique

Accurate segmentation of cardiac MRI is of great significance in the field of medical image processing. It aims to accurately extract cardiac structures, such as ventricles, atria, myocardium, etc., from cardiac MR images to assist doctors in accurately diagnosing and treating cardiac diseases. At present, the research methods of cardiac MR image segmentation are mainly divided into traditional methods and deep learning-based methods. Traditional methods are difficult to handle complex cardiac structures in cardiac MRI segmentation, resulting in poor segmentation results, while deep learning methods can achieve better results. Capture complex features in cardiac MR images well. As a representative deep learning architecture, U-Net adopts an encoder-decoder structure and introduces skip connections, which solves the information loss problem of traditional convolutional neural networks in segmentation tasks and provides a basis for the research and development of cardiac MRI segmentation. The application brought important breakthroughs. However, the problem of insufficient feature abstraction capabilities and lack of learning contextual relationships between pixels leads to the complexity of segmentation.

Contents of the invention

In order to overcome the shortcomings of the above technologies, the present invention provides a cardiac MRI segmentation method based on context cascade attention that can better capture and represent complex data features.

The technical solution adopted by the present invention to overcome its technical problems is:

A cardiac MRI segmentation method based on context cascade attention, including the following steps:

a) Collect cardiac MRI data of n subjects to obtain MRI data set s, s={s ₁ , s ₂ ,..., s _i ,..., s _n }, s _i is the i-th subject Subject's cardiac MRI data, i∈{1,2,...,n};

b) Perform preprocessing operations on the MRI data set s to obtain the preprocessed data set F, F={F ₁ , F ₂ ,..., F _i ,..., F _n }, F _i is the i-th Preprocessed two-dimensional image data;

c) Divide the preprocessed data set F into a training set, a test set, and a verification set;

d) Establish a segmentation network model consisting of an encoder and a decoder;

e) Input the preprocessed two-dimensional image data F _i into the encoder of the segmentation network model, and output the feature map Feature map/> Feature map/> Feature map/>

f) Convert the feature map to Feature map/> Feature map/> Feature map/> Input to the decoder of the segmentation network model, and the output is the predicted segmentation image/>

g) Train the segmentation network model and obtain the optimized segmentation network model.

Further, in step a), cardiac MRI data of n subjects containing three structures of LV, RV, and MYO are collected from ACDC2017 public data to obtain MRI data set s.

Preferably, n=100 in step a).

Further, step b) includes the following steps:

b-1) Resample the cardiac MRI data s _i of the i-th subject slice by slice along the z-axis, with the pixel spacing in the x-axis direction being 1.5 and the pixel spacing in the y-axis direction being 1.5;

b-2) Perform a 2D center clipping operation with a crop size of 224×224 on the resampled cardiac MRI data s _i to obtain the clipped data F _i ′, and normalize the clipped data F _i ′. The preprocessed two-dimensional image data _Fi is obtained.

Preferably, in step c), the preprocessed data set F is divided into a training set, a test set, and a verification set in a ratio of 7:2:1.

Further, step e) includes the following steps:

e-1) The encoder of the segmentation network model consists of the first residual initialization module, the first maximum pooling layer, the second residual initialization module, the second maximum pooling layer, the third residual initialization module, and the third maximum pooling ization layer and the fourth residual initial module;

e-2) The first residual initial module is composed of the first branch, the second branch, the third branch, the fourth branch, and the fifth branch. The first branch is composed of a convolution layer, and the second branch is composed of an average pooling layer in turn. , convolution layer, the third branch is composed of convolution layer and BN layer in sequence, the fourth branch is composed of first convolution layer, second convolution layer and BN layer in sequence, and the fifth branch is composed of first convolution layer in sequence. , the second convolution layer, the first BN layer, the third convolution layer, and the second BN layer. The preprocessed two-dimensional image data F _i is input into the first branch, and the feature map is output. Input the preprocessed two-dimensional image data F _i into the second branch, and output the feature map/> Input the preprocessed two-dimensional image data F _i into the third branch, and output the feature map/> Input the preprocessed two-dimensional image data F _i into the fourth branch, and output the feature map/> Input the preprocessed two-dimensional image data F _i into the fifth branch, and output the feature map/> Convert the feature map/> feature map Feature map/> Feature map/> Perform splicing operation to obtain feature map/> Convert the feature map/> with feature map The addition operation obtains the feature map/> e-3) Convert the feature map/> Input to the first maximum pooling layer, and the output is the feature map/> e-4) The second residual initial module is composed of the first branch, the second branch, the third branch, the fourth branch, and the fifth branch. The first branch is composed of a convolution layer, and the second branch is composed of an average pooling layer in turn. , convolution layer, the third branch is composed of convolution layer and BN layer in sequence, the fourth branch is composed of first convolution layer, second convolution layer and BN layer in sequence, and the fifth branch is composed of first convolution layer in sequence. , the second convolution layer, the first BN layer, the third convolution layer, and the second BN layer, and the feature map/> Input to the first branch and output the feature map/> Convert the feature map/> Input to the second branch, and the output is the feature map/> The feature map Input to the third branch, and the output is the feature map/> Convert the feature map/> Input to the fourth branch, and the output is the feature map/> Convert the feature map/> Input to the fifth branch, and the output is the feature map/> Convert the feature map/> Feature map/> Feature map/> Feature map/> Perform splicing operation to obtain feature map/> Convert the feature map/> and feature map/> The addition operation obtains the feature map/> e-5) Convert the feature map/> Input to the second maximum pooling layer, and the output is the feature map/> e-6) The third residual initial module is composed of the first branch, the second branch, the third branch, the fourth branch, and the fifth branch. The first branch is composed of a convolution layer, and the second branch is composed of an average pooling layer in turn. , convolution layer, the third branch is composed of convolution layer and BN layer in sequence, the fourth branch is composed of first convolution layer, second convolution layer and BN layer in sequence, and the fifth branch is composed of first convolution layer in sequence. , the second convolution layer, the first BN layer, the third convolution layer, and the second BN layer, and the feature map/> Input to the first branch and output the feature map/> Convert the feature map/> Input to the second branch, and the output is the feature map/> Convert the feature map/> Input to the third branch, and the output is the feature map/> Convert the feature map/> Input to the fourth branch, and the output is the feature map/> Convert the feature map/> Input to the fifth branch, and the output is the feature map/> Convert the feature map/> Feature map/> Feature map/> Feature map/> Perform splicing operation to obtain feature map/> Convert the feature map/> and feature map/> The addition operation obtains the feature map/> e-7) Convert the feature map/> Input to the third maximum pooling layer, and the output is the feature map/> e-8) The fourth residual initial module is composed of the first branch, the second branch, the third branch, the fourth branch, and the fifth branch. The first branch is composed of a convolution layer, and the second branch is composed of an average pooling layer in turn. , convolution layer, the third branch is composed of convolution layer and BN layer in sequence, the fourth branch is composed of first convolution layer, second convolution layer and BN layer in sequence, and the fifth branch is composed of first convolution layer in sequence. , the second convolution layer, the first BN layer, the third convolution layer, and the second BN layer, and the feature map/> Input to the first branch and output the feature map/> Convert the feature map/> Input to the second branch, and the output is the feature map/> Convert the feature map/> Input to the third branch, and the output is the feature map/> Convert the feature map/> Input to the fourth branch, and the output is the feature map/> Convert the feature map/> Input to the fifth branch, and the output is the feature map/> The feature map Feature map/> Feature map/> Feature map/> Perform splicing operation to obtain feature map/> The feature map with feature map/> The addition operation obtains the feature map/> Preferably, in step e-2), the convolution kernel size of the convolution layer of the first branch is 1×1, the convolution kernel size of the convolution layer of the second branch is 1×1, and the convolution kernel size of the third branch is 1×1. The convolution kernel size is 1×1. The convolution kernel size of the first convolution layer of the fourth branch is 1×1. The convolution kernel size of the second convolution layer is 5×5. The padding is 2. The convolution kernel size of the first convolution layer of the branch is 1×1, the convolution kernel size of the second convolution layer is 3×3, and the convolution kernel size of the third convolution layer is 3×3; step e- In 4), the convolution kernel size of the convolution layer of the first branch is 1×1, the convolution kernel size of the convolution layer of the second branch is 1×1, and the convolution kernel size of the convolution layer of the third branch is 1×1, the convolution kernel size of the first convolution layer of the fourth branch is 1×1, the convolution kernel size of the second convolution layer is 5×5, padding is 2, the first convolution of the fifth branch The convolution kernel size of the layer is 1×1, the convolution kernel size of the second convolution layer is 3×3, and the convolution kernel size of the third convolution layer is 3×3; the first branch in step e-6) The convolution kernel size of the convolution layer is 1×1, the convolution kernel size of the convolution layer of the second branch is 1×1, the convolution kernel size of the convolution layer of the third branch is 1×1, and the convolution kernel size of the fourth branch is 1×1. The convolution kernel size of the first convolution layer of the branch is 1×1, the convolution kernel size of the second convolution layer is 5×5, and the padding is 2. The convolution kernel size of the first convolution layer of the fifth branch is is 1×1, the convolution kernel size of the second convolution layer is 3×3, and the convolution kernel size of the third convolution layer is 3×3; the convolution of the convolution layer of the first branch in step e-8) The convolution kernel size is 1×1, the convolution kernel size of the convolution layer of the second branch is 1×1, the convolution kernel size of the convolution layer of the third branch is 1×1, and the first convolution of the fourth branch The convolution kernel size of the layer is 1×1, the convolution kernel size of the second convolution layer is 5×5, and the padding is 2. The convolution kernel size of the first convolution layer of the fifth branch is 1×1, and the convolution kernel size of the second convolution layer is 5×5. The convolution kernel size of the second convolution layer is 3×3, and the convolution kernel size of the third convolution layer is 3×3; the convolution kernel size of the first maximum pooling layer in step e-3) is 2×2. ; The convolution kernel size of the second maximum pooling layer in step e-5) is 2×2; the convolution kernel size of the third maximum pooling layer in step e-7) is 2×2.

Further, step f) includes the following steps:

f-1) The decoder of the segmentation network model consists of Conv-block1, the first attention gating module, the first upsampling layer, the first contextual attention module, the first convolution layer, Conv-block2, and the second attention Gating module, second upsampling layer, second contextual attention module, second convolutional layer, Conv-block3, third attention gating module, third upsampling layer, third contextual attention module, third Composed of convolutional layer, Conv-block4, fourth attention gating module, fourth contextual attention module, and fourth convolutional layer;

f-2) Conv-block4 consists of a convolution layer, a BatchNorm layer, and a ReLU activation function in sequence. The feature map Input to Conv-block4 and output the feature map/> The fourth attention gating module consists of the first convolution layer, the first BN layer, the second convolution layer, the second BN layer, the ReLU activation function, the third convolution layer, the third BN layer, and the sigmoid function. Feature map/> It is input to the first convolutional layer and the first BN layer of the fourth attention gating module in turn, and the output is a feature map. Convert the feature map/> It is input to the second convolutional layer and the second BN layer of the fourth attention gating module in turn, and the output is the feature map/> Convert the feature map/> with feature map/> Add up to get the feature map/> Convert the feature map/> It is input to the ReLU activation function of the fourth attention gating module, the third convolution layer, the third BN layer, and the sigmoid function in sequence, and the output is a feature map/> Convert the feature map/> and feature map/> Multiply to get the feature map/> The fourth contextual attention module consists of the first convolution layer, the second convolution layer, the global maximum pooling layer, the third convolution layer, the fourth convolution layer, and the sigmoid function. The feature map/> It is input to the first convolutional layer and the second convolutional layer of the fourth contextual attention module in turn, and the output is a feature map/> Convert the feature map/> Input to the global maximum pooling layer of the fourth contextual attention module, and the output is the feature map/> Convert the feature map/> It is input to the third convolutional layer and the fourth convolutional layer of the fourth context attention module in turn, and the output is the feature map/> Convert the feature map/> and feature map/> Multiply to get the feature map/> The feature map and feature map/> Add up to get the feature map/> Convert the feature map/> Input to the sigmoid function of the fourth context attention module, and the output is the feature map/> Convert the feature map/> Input to the fourth convolutional layer to obtain the feature map f-3) Conv-block3 consists of a convolution layer, a BatchNorm layer, and a ReLU activation function in sequence. The feature map/> Input into Conv-block3 and output the feature map/> Convert the feature map/> Input to the third upsampling layer, and the output is the feature map/> The third attention gating module consists of the first convolution layer, the first BN layer, the second convolution layer, the second BN layer, the ReLU activation function, the third convolution layer, the third BN layer, and the sigmoid function. Feature map/> It is input to the first convolutional layer and the first BN layer of the third attention gating module in turn, and the output is the feature map/> Convert the feature map/> It is input to the second convolutional layer and the second BN layer of the third attention gating module in turn, and the output is the feature map/> Convert the feature map/> with feature map Add up to get the feature map/> Convert the feature map/> Input to the ReLU activation function of the third attention gating module, the third convolution layer, the third BN layer, and the sigmoid function in sequence, and the output is the feature map/> Convert the feature map/> and feature map/> Multiply to get the feature map/> Convert the feature map/> and feature map/> Cascade to obtain feature map/> The third contextual attention module consists of the first convolution layer, the second convolution layer, the global maximum pooling layer, the third convolution layer, the fourth convolution layer, and the sigmoid function. The feature map/> It is input to the first convolutional layer and the second convolutional layer of the third contextual attention module in turn, and the output is a feature map/> Convert the feature map/> Input to the global maximum pooling layer of the third contextual attention module, and the output is the feature map/> Convert the feature map/> It is input to the third convolutional layer and the fourth convolutional layer of the third context attention module in turn, and the output is the feature map/> Convert the feature map/> and feature map/> Multiply to get the feature map/> Convert the feature map/> and feature map/> Add up to get the feature map/> Convert the feature map/> Input to the sigmoid function of the third contextual attention module, and the output is the feature map/> Convert the feature map/> Input to the third convolutional layer to obtain the feature map/> f-4) Conv-block2 consists of a convolution layer, a BatchNorm layer, and a ReLU activation function in sequence. The feature map/> Input to Conv-block2 and output the feature map/> Convert the feature map/> Input to the second upsampling layer, and the output is the feature map/> The second attention gating module consists of the first convolution layer, the first BN layer, the second convolution layer, the second BN layer, the ReLU activation function, the third convolution layer, the third BN layer, and the sigmoid function. Feature map/> It is input to the first convolutional layer and the first BN layer of the second attention gating module in turn, and the output is the feature map/> Convert the feature map/> It is input to the second convolutional layer and the second BN layer of the second attention gating module in turn, and the output is a feature map/> Convert the feature map/> and feature map/> Add up to get the feature map/> Convert the feature map/> It is input into the ReLU activation function of the second attention gating module, the third convolution layer, the third BN layer, and the sigmoid function in sequence, and the output is a feature map/> The feature map and feature map/> Multiply to get the feature map/> Convert the feature map/> with feature map/> Cascade to obtain feature map/> The second contextual attention module consists of the first convolution layer, the second convolution layer, the global maximum pooling layer, the third convolution layer, the fourth convolution layer, and the sigmoid function. The feature map/> It is input to the first convolutional layer and the second convolutional layer of the second context attention module in turn, and the output is a feature map/> Convert the feature map/> Input to the global maximum pooling layer of the second contextual attention module, and the output is the feature map/> Convert the feature map/> It is input to the third convolutional layer and the fourth convolutional layer of the second context attention module in turn, and the output is the feature map/> Convert the feature map/> and feature map/> Multiply to get the feature map/> Convert the feature map/> and feature map/> Add up to get the feature map/> Convert the feature map/> Input to the sigmoid function of the second context attention module, and the output is the feature map/> Convert the feature map/> Input to the second convolutional layer to obtain the feature map/> f-5) Conv-block1 consists of a convolution layer, a BatchNorm layer, and a ReLU activation function in sequence. The feature map/> Input into Conv-block1 and output the feature map/> Convert the feature map/> Input to the first upsampling layer, and the output is the feature map/> The first attention gating module consists of the first convolution layer, the first BN layer, the second convolution layer, the second BN layer, the ReLU activation function, the third convolution layer, the third BN layer, and the sigmoid function. Feature map/> It is input into the first convolutional layer and the first BN layer of the first attention gating module in turn, and the output is the feature map/> Convert the feature map/> It is input to the second convolutional layer and the second BN layer of the first attention gating module in turn, and the output is the feature map/> The feature map and feature map/> Add up to get the feature map/> Convert the feature map/> Input to the ReLU activation function of the first attention gating module, the third convolution layer, the third BN layer, and the sigmoid function in sequence, and the output is the feature map/> Convert the feature map/> and feature map/> Multiply to get the feature map/> Convert the feature map/> and feature map/> Cascade to obtain feature map/> The first contextual attention module consists of the first convolution layer, the second convolution layer, the global maximum pooling layer, the third convolution layer, the fourth convolution layer, and the sigmoid function. The feature map/> It is input to the first convolutional layer and the second convolutional layer of the first context attention module in turn, and the output is the feature map/> Convert the feature map/> Input to the global maximum pooling layer of the first contextual attention module, and the output is the feature map/> Convert the feature map/> It is input to the third convolutional layer and the fourth convolutional layer of the first context attention module in turn, and the output is the feature map/> Convert the feature map/> and feature map/> Multiply to get the feature map/> Convert the feature map/> and feature map/> Add up to get the feature map/> Convert the feature map/> Input to the sigmoid function of the first contextual attention module, and the output is the feature map/> Convert the feature map/> Input to the first convolutional layer to obtain the feature map/> f-6) Convert the feature map/> Feature map/> Feature map/> Feature map/> Add the residuals to obtain the feature map/>

Preferably, the convolution kernel size of the convolution layer of Conv-block4 in step f-2) is 3×3, and the padding is 1; the first convolution layer, the second convolution layer of the fourth attention gating module, The convolution kernel sizes of the third convolutional layer are all 1×1; the convolution kernel sizes of the first, second, and third convolutional layers of the fourth contextual attention module are all 3×3. , padding is 1, the convolution kernel size of the fourth convolutional layer of the fourth contextual attention module is 1×1; the convolutional kernel size of the fourth convolutional layer of the decoder is 1×1; step f-3) The convolution kernel size of the convolution layer of Conv-block3 is 3×3, and the padding is 1; the convolution of the first convolution layer, the second convolution layer, and the third convolution layer of the third attention gating module The kernel sizes are all 1×1; the convolution kernel size of the third upsampling layer is 2×2; the convolutions of the first convolutional layer, the second convolutional layer, and the third convolutional layer of the third contextual attention module The kernel sizes are all 3×3, padding is 1, the convolution kernel size of the fourth convolutional layer of the third contextual attention module is 1×1; the convolutional kernel size of the third convolutional layer of the decoder is 1× 1; f-4) The convolution kernel size of the convolution layer of Conv-block2 is 3×3, and the padding is 1; the first convolution layer, the second convolution layer, and the third convolution layer of the second attention gating module The convolution kernel size of the convolution layer is 1×1; the convolution kernel size of the second upsampling layer is 2×2; the first convolution layer, the second convolution layer, and the third convolution layer of the second context attention module The convolution kernel size of the convolutional layer is 3×3, and the padding is 1. The convolution kernel size of the fourth convolutional layer of the second contextual attention module is 1×1; the convolution kernel size of the second convolutional layer of the decoder is 1×1. The convolution kernel size is 1 × 1; the convolution kernel size of the convolution layer of Conv-block1 in f-5) is 3 × 3, and the padding is 1; the first convolution layer and the second convolution layer of the first attention gating module The convolution kernel size of the convolution layer and the third convolution layer is 1×1; the convolution kernel size of the first upsampling layer is 2×2; the first convolution layer and the second convolution layer of the first context attention module The convolution kernel size of the convolution layer and the third convolution layer is 3 × 3, and the padding is 1. The convolution kernel size of the fourth convolution layer of the first context attention module is 1 × 1; the convolution kernel size of the decoder is 1 × 1. The convolution kernel size of a convolutional layer is 1×1. Further, in step g), the Dice loss and cross-entropy loss are summed to obtain the total loss, and the Adam optimizer is used to train the segmentation network model using the total loss to obtain the optimized segmentation network model. The batch size during training is set to 32, and iteration The period is set to 200 and the learning rate is set to 0.001.

The beneficial effects of the present invention are: introducing a residual initial module in the encoder to better learn effective feature representations and improve the performance and generalization ability of the model. The complementary information of different layers is utilized in the decoder through cascade operations to refine the features of each layer, while the contextual attention module is used to explore the contextual information of each layer by retaining local information and compressing global information, and suppressing unimportant information. information area to highlight salient features, thereby improving the accuracy of segmentation.

Description of drawings

Figure 1 is a structural diagram of the segmentation network model of the present invention;

Figure 2 is a structural diagram of the residual initial module of the present invention;

Figure 3 is a structural diagram of the attention gating module of the present invention;

Figure 4 is a structural diagram of the contextual attention module of the present invention.

Detailed ways

The present invention will be further described below in conjunction with Figures 1 to 4.

A cardiac MRI segmentation method based on context cascade attention, including the following steps:

a) Collect cardiac MRI data of n subjects to obtain MRI data set s, s={s ₁ , s ₂ ,..., s _i ,..., s _n }, s _i is the i-th subject The subject's cardiac MRI data, i∈{1,2,...,n}.

b) Perform preprocessing operations on the MRI data set s to obtain the preprocessed data set F, F={F ₁ , F ₂ ,..., F _i ,..., F _n }, F _i is the i-th preprocessed two-dimensional image data.

c) Divide the preprocessed data set F into a training set, a test set, and a verification set.

d) Establish a segmentation network model consisting of an encoder and a decoder.

e) Input the preprocessed two-dimensional image data F _i into the encoder of the segmentation network model, and output the feature map Feature map/> Feature map/> Feature map/>

f) Convert the feature map to Feature map/> Feature map/> Feature map/> Input to the decoder of the segmentation network model, and the output is the predicted segmentation image/>

g) Train the segmentation network model and obtain the optimized segmentation network model.

The residual initialization module is used in the encoder to better capture and represent complex data features, and the features of multi-scale and multi-resolution spatial representation are learned through multi-layer context cascade operations in the decoder.

In one embodiment of the present invention, in step a), cardiac MRI data of n subjects containing three structures of LV, RV, and MYO are collected from ACDC2017 public data to obtain MRI data set s. In this embodiment, preferably, n=100 in step a).

In one embodiment of the invention, step b) includes the following steps:

b-1) The cardiac MRI data s _i of the i-th subject are resampled slice by slice along the z-axis, with the pixel spacing in the x-axis direction being 1.5 and the pixel spacing in the y-axis direction being 1.5.

b-2) Perform a 2D center clipping operation with a crop size of 224×224 on the resampled cardiac MRI data s _i to obtain the clipped data F _i ′. In order to ensure the consistency of the data, the clipped data F _i ′ Perform normalization processing to obtain preprocessed two-dimensional image data _Fi .

In one embodiment of the present invention, in step c), the preprocessed data set F is divided into a training set, a test set, and a verification set in a ratio of 7:2:1.

In one embodiment of the present invention, step e) includes the following steps:

e-1) The encoder of the segmentation network model consists of the first residual initialization module, the first maximum pooling layer, the second residual initialization module, the second maximum pooling layer, the third residual initialization module, and the third maximum pooling ization layer and the fourth residual initial module.

e-2) The first residual initial module is composed of the first branch, the second branch, the third branch, the fourth branch, and the fifth branch. The first branch is composed of a convolution layer, and the second branch is composed of an average pooling layer in turn. , convolution layer, the third branch is composed of convolution layer and BN layer in sequence, the fourth branch is composed of first convolution layer, second convolution layer and BN layer in sequence, and the fifth branch is composed of first convolution layer in sequence. , the second convolution layer, the first BN layer, the third convolution layer, and the second BN layer. The preprocessed two-dimensional image data F _i is input into the first branch, and the feature map is output. Input the preprocessed two-dimensional image data F _i into the second branch, and output the feature map/> Input the preprocessed two-dimensional image data F _i into the third branch, and output the feature map/> Input the preprocessed two-dimensional image data F _i into the fourth branch, and output the feature map/> Input the preprocessed two-dimensional image data F _i into the fifth branch, and output the feature map/> Convert the feature map/> feature map Feature map/> Feature map/> Perform splicing operation to obtain feature map/> Convert the feature map/> with feature map The addition operation obtains the feature map/> e-3) Convert the feature map/> Input to the first maximum pooling layer, and the output is the feature map/> e-4) The second residual initial module is composed of the first branch, the second branch, the third branch, the fourth branch, and the fifth branch. The first branch is composed of a convolution layer, and the second branch is composed of an average pooling layer in turn. , convolution layer, the third branch is composed of convolution layer and BN layer in sequence, the fourth branch is composed of first convolution layer, second convolution layer and BN layer in sequence, and the fifth branch is composed of first convolution layer in sequence. , the second convolution layer, the first BN layer, the third convolution layer, and the second BN layer, and the feature map/> Input to the first branch and output the feature map/> Convert the feature map/> Input to the second branch, and the output is the feature map/> The feature map Input to the third branch, and the output is the feature map/> Convert the feature map/> Input to the fourth branch, and the output is the feature map/> Convert the feature map/> Input to the fifth branch, and the output is the feature map/> Convert the feature map/> Feature map/> Feature map/> Feature map/> Perform splicing operation to obtain feature map/> Convert the feature map/> and feature map/> The addition operation obtains the feature map/> e-5) Convert the feature map/> Input to the second maximum pooling layer, and the output is the feature map/> e-6) The third residual initial module is composed of the first branch, the second branch, the third branch, the fourth branch, and the fifth branch. The first branch is composed of a convolution layer, and the second branch is composed of an average pooling layer in turn. , convolution layer, the third branch is composed of convolution layer and BN layer in sequence, the fourth branch is composed of first convolution layer, second convolution layer and BN layer in sequence, and the fifth branch is composed of first convolution layer in sequence. , the second convolution layer, the first BN layer, the third convolution layer, and the second BN layer, and the feature map/> Input to the first branch and output the feature map/> Convert the feature map/> Input to the second branch, and the output is the feature map/> Convert the feature map/> Input to the third branch, and the output is the feature map/> Convert the feature map/> Input to the fourth branch, and the output is the feature map/> Convert the feature map/> Input to the fifth branch, and the output is the feature map/> Convert the feature map/> Feature map/> Feature map/> Feature map/> Perform splicing operation to obtain feature map/> Convert the feature map/> and feature map/> The addition operation obtains the feature map/> e-7) Convert the feature map/> Input to the third maximum pooling layer, and the output is the feature map/> e-8) The fourth residual initial module is composed of the first branch, the second branch, the third branch, the fourth branch, and the fifth branch. The first branch is composed of a convolution layer, and the second branch is composed of an average pooling layer in turn. , convolution layer, the third branch is composed of convolution layer and BN layer in sequence, the fourth branch is composed of first convolution layer, second convolution layer and BN layer in sequence, and the fifth branch is composed of first convolution layer in sequence. , the second convolution layer, the first BN layer, the third convolution layer, and the second BN layer, and the feature map/> Input to the first branch and output the feature map/> Convert the feature map/> Input to the second branch, and the output is the feature map/> Convert the feature map/> Input to the third branch, and the output is the feature map/> Convert the feature map/> Input to the fourth branch, and the output is the feature map/> Convert the feature map/> Input to the fifth branch, and the output is the feature map/> Convert the feature map/> Feature map/> Feature map/> Feature map/> Perform splicing operation to obtain feature map/> Convert the feature map/> and feature map/> The addition operation obtains the feature map/> In this embodiment, preferably, in step e-2), the convolution kernel size of the convolution layer of the first branch is 1×1, the convolution kernel size of the convolution layer of the second branch is 1×1, and the convolution kernel size of the convolution layer of the second branch is 1×1. The convolution kernel size of the three-branch convolution layer is 1×1, the convolution kernel size of the first convolution layer of the fourth branch is 1×1, and the convolution kernel size of the second convolution layer is 5×5. padding is 2, the convolution kernel size of the first convolution layer of the fifth branch is 1×1, the convolution kernel size of the second convolution layer is 3×3, and the convolution kernel size of the third convolution layer is 3 ×3; in step e-4), the convolution kernel size of the convolution layer of the first branch is 1×1, the convolution kernel size of the convolution layer of the second branch is 1×1, and the convolution kernel size of the convolution layer of the third branch is 1×1. The convolution kernel size is 1×1. The convolution kernel size of the first convolution layer of the fourth branch is 1×1. The convolution kernel size of the second convolution layer is 5×5. The padding is 2. The convolution kernel size of the first convolution layer of the branch is 1×1, the convolution kernel size of the second convolution layer is 3×3, and the convolution kernel size of the third convolution layer is 3×3; step e- In 6), the convolution kernel size of the convolution layer of the first branch is 1×1, the convolution kernel size of the convolution layer of the second branch is 1×1, and the convolution kernel size of the convolution layer of the third branch is 1×1, the convolution kernel size of the first convolution layer of the fourth branch is 1×1, the convolution kernel size of the second convolution layer is 5×5, padding is 2, the first convolution of the fifth branch The convolution kernel size of the layer is 1×1, the convolution kernel size of the second convolution layer is 3×3, and the convolution kernel size of the third convolution layer is 3×3; the first branch in step e-8) The convolution kernel size of the convolution layer is 1×1, the convolution kernel size of the convolution layer of the second branch is 1×1, the convolution kernel size of the convolution layer of the third branch is 1×1, and the convolution kernel size of the fourth branch is 1×1. The convolution kernel size of the first convolution layer of the branch is 1×1, the convolution kernel size of the second convolution layer is 5×5, and the padding is 2. The convolution kernel size of the first convolution layer of the fifth branch is is 1×1, the convolution kernel size of the second convolution layer is 3×3, and the convolution kernel size of the third convolution layer is 3×3; the convolution of the first maximum pooling layer in step e-3) The kernel size is 2×2; the convolution kernel size of the second maximum pooling layer in step e-5) is 2×2; the convolution kernel size of the third maximum pooling layer in step e-7) is 2×2 . In one embodiment of the present invention, step f) includes the following steps:

f-1) The decoder of the segmentation network model consists of Conv-block1, the first attention gating module, the first upsampling layer, the first contextual attention module, the first convolution layer, Conv-block2, and the second attention Gating module, second upsampling layer, second contextual attention module, second convolutional layer, Conv-block3, third attention gating module, third upsampling layer, third contextual attention module, third It is composed of convolutional layer, Conv-block4, fourth attention gating module, fourth contextual attention module and fourth convolutional layer.

f-2) Conv-block4 consists of a convolution layer, a BatchNorm layer, and a ReLU activation function in sequence. The feature map Input to Conv-block4 and output the feature map/> The fourth attention gating module consists of the first convolution layer, the first BN layer, the second convolution layer, the second BN layer, the ReLU activation function, the third convolution layer, the third BN layer, and the sigmoid function. Feature map/> It is input to the first convolutional layer and the first BN layer of the fourth attention gating module in turn, and the output is a feature map. Convert the feature map/> It is input to the second convolutional layer and the second BN layer of the fourth attention gating module in turn, and the output is the feature map/> Convert the feature map/> and feature map/> Add up to get the feature map/> Convert the feature map/> It is input to the ReLU activation function of the fourth attention gating module, the third convolution layer, the third BN layer, and the sigmoid function in sequence, and the output is a feature map/> Convert the feature map/> and feature map/> Multiply to get the feature map/> The fourth contextual attention module consists of the first convolution layer, the second convolution layer, the global maximum pooling layer, the third convolution layer, the fourth convolution layer, and the sigmoid function. The feature map/> It is input to the first convolutional layer and the second convolutional layer of the fourth contextual attention module in turn, and the output is a feature map/> Convert the feature map/> Input to the global maximum pooling layer of the fourth contextual attention module, and the output is the feature map/> Convert the feature map/> It is input to the third convolutional layer and the fourth convolutional layer of the fourth context attention module in turn, and the output is the feature map/> Convert the feature map/> and feature map/> Multiply to get the feature map/> The feature map and feature map/> Add up to get the feature map/> Convert the feature map/> Input to the sigmoid function of the fourth context attention module, and the output is the feature map/> Convert the feature map/> Input to the fourth convolutional layer to obtain the feature map f-3) Conv-block3 consists of a convolution layer, a BatchNorm layer, and a ReLU activation function in sequence. The feature map/> Input into Conv-block3 and output the feature map/> Convert the feature map/> Input to the third upsampling layer, and the output is the feature map/> The third attention gating module consists of the first convolution layer, the first BN layer, the second convolution layer, the second BN layer, the ReLU activation function, the third convolution layer, the third BN layer, and the sigmoid function. Feature map/> It is input to the first convolutional layer and the first BN layer of the third attention gating module in turn, and the output is the feature map/> Convert the feature map/> It is input to the second convolutional layer and the second BN layer of the third attention gating module in turn, and the output is the feature map/> Convert the feature map/> with feature map Add up to get the feature map/> Convert the feature map/> Input to the ReLU activation function of the third attention gating module, the third convolution layer, the third BN layer, and the sigmoid function in sequence, and the output is the feature map/> Convert the feature map/> and feature map/> Multiply to get the feature map/> Convert the feature map/> and feature map/> Cascade to obtain feature map/> The third contextual attention module consists of the first convolution layer, the second convolution layer, the global maximum pooling layer, the third convolution layer, the fourth convolution layer, and the sigmoid function. The feature map/> It is input to the first convolutional layer and the second convolutional layer of the third contextual attention module in turn, and the output is a feature map/> Convert the feature map/> Input to the global maximum pooling layer of the third contextual attention module, and the output is the feature map/> Convert the feature map/> It is input to the third convolutional layer and the fourth convolutional layer of the third context attention module in turn, and the output is the feature map/> Convert the feature map/> and feature map/> Multiply to get the feature map Convert the feature map/> and feature map/> Add up to get the feature map/> Convert the feature map/> Input to the sigmoid function of the third contextual attention module, and the output is the feature map/> Convert the feature map/> Input to the third convolutional layer to obtain the feature map/> f-4) Conv-block2 consists of a convolution layer, a BatchNorm layer, and a ReLU activation function in sequence. The feature map/> Input to Conv-block2 and output the feature map/> Convert the feature map/> Input to the second upsampling layer, and the output is the feature map/> The second attention gating module consists of the first convolution layer, the first BN layer, the second convolution layer, the second BN layer, the ReLU activation function, the third convolution layer, the third BN layer, and the sigmoid function. Feature map/> It is input to the first convolutional layer and the first BN layer of the second attention gating module in turn, and the output is the feature map/> Convert the feature map/> It is input to the second convolutional layer and the second BN layer of the second attention gating module in turn, and the output is a feature map/> Convert the feature map/> and feature map/> Add up to get the feature map/> Convert the feature map/> It is input into the ReLU activation function of the second attention gating module, the third convolution layer, the third BN layer, and the sigmoid function in sequence, and the output is a feature map/> Convert the feature map/> and feature map/> Multiply to get the feature map/> Convert the feature map/> and feature map/> Cascade to obtain feature map/> The second contextual attention module consists of the first convolution layer, the second convolution layer, the global maximum pooling layer, the third convolution layer, the fourth convolution layer, and the sigmoid function. The feature map/> It is input to the first convolutional layer and the second convolutional layer of the second context attention module in turn, and the output is a feature map/> Convert the feature map/> Input to the global maximum pooling layer of the second contextual attention module, and the output is the feature map/> Convert the feature map/> It is input to the third convolutional layer and the fourth convolutional layer of the second context attention module in turn, and the output is the feature map/> Convert the feature map/> and feature map/> Multiply to get the feature map Convert the feature map/> and feature map/> Add up to get the feature map/> Convert the feature map/> Input to the sigmoid function of the second context attention module, and the output is the feature map/> Convert the feature map/> Input to the second convolutional layer to obtain the feature map/> f-5) Conv-block1 consists of a convolution layer, a BatchNorm layer, and a ReLU activation function in sequence. The feature map/> Input into Conv-block1 and output the feature map/> Convert the feature map/> Input to the first upsampling layer, and the output is the feature map/> The first attention gating module consists of the first convolution layer, the first BN layer, the second convolution layer, the second BN layer, the ReLU activation function, the third convolution layer, the third BN layer, and the sigmoid function. Feature map/> It is input into the first convolutional layer and the first BN layer of the first attention gating module in turn, and the output is the feature map/> Convert the feature map/> It is input to the second convolutional layer and the second BN layer of the first attention gating module in turn, and the output is the feature map/> Convert the feature map/> and feature map/> Add up to get the feature map/> Convert the feature map/> Input to the ReLU activation function of the first attention gating module, the third convolution layer, the third BN layer, and the sigmoid function in sequence, and the output is the feature map/> The feature map and feature map/> Multiply to get the feature map/> Convert the feature map/> and feature map/> Cascade to obtain feature map/> The first contextual attention module consists of the first convolution layer, the second convolution layer, the global maximum pooling layer, the third convolution layer, the fourth convolution layer, and the sigmoid function. The feature map/> It is input to the first convolutional layer and the second convolutional layer of the first context attention module in turn, and the output is the feature map/> Convert the feature map/> Input to the global maximum pooling layer of the first contextual attention module, and the output is the feature map/> Convert the feature map/> It is input to the third convolutional layer and the fourth convolutional layer of the first context attention module in turn, and the output is the feature map/> Convert the feature map/> and feature map/> Multiply to get the feature map/> Convert the feature map/> and feature map/> Add up to get the feature map/> Convert the feature map/> Input to the sigmoid function of the first contextual attention module, and the output is the feature map/> Convert the feature map/> Input to the first convolutional layer to obtain the feature map/> f-6) Convert the feature map/> Feature map/> Feature map/> Feature map/> Add the residuals to obtain the feature map/>

In this embodiment, preferably, the convolution kernel size of the convolution layer of Conv-block4 in step f-2) is 3×3, and the padding is 1; the first convolution layer of the fourth attention gating module, The convolution kernel sizes of the second convolution layer and the third convolution layer are both 1 × 1; the convolution kernels of the first convolution layer, the second convolution layer, and the third convolution layer of the fourth contextual attention module The sizes are all 3×3, padding is 1, the convolution kernel size of the fourth convolutional layer of the fourth contextual attention module is 1×1; the convolutional kernel size of the fourth convolutional layer of the decoder is 1×1 ; The convolution kernel size of the convolution layer of Conv-block3 in step f-3) is 3×3, and the padding is 1; the first convolution layer, the second convolution layer, and the third convolution layer of the third attention gating module The convolution kernel size of the convolutional layer is 1×1; the convolution kernel size of the third upsampling layer is 2×2; the first convolutional layer, the second convolutional layer, and the third convolutional layer of the third contextual attention module The convolution kernel size of the convolutional layer is 3×3, and the padding is 1. The convolution kernel size of the fourth convolutional layer of the third contextual attention module is 1×1; the convolution kernel size of the third convolutional layer of the decoder is 1×1. The convolution kernel size is 1 × 1; the convolution kernel size of the convolution layer of Conv-block2 in f-4) is 3 × 3, and the padding is 1; the first convolution layer and the second convolution layer of the second attention gating module The convolution kernel size of the convolution layer and the third convolution layer is 1 × 1; the convolution kernel size of the second upsampling layer is 2 × 2; the first convolution layer and the second convolution layer of the second context attention module The convolution kernel size of the convolution layer and the third convolution layer is 3 × 3, and the padding is 1. The convolution kernel size of the fourth convolution layer of the second context attention module is 1 × 1; the convolution kernel size of the decoder is 1 × 1. The convolution kernel size of the second convolutional layer is 1×1; the convolution kernel size of the convolutional layer of Conv-block1 in f-5) is 3×3, and the padding is 1; the first attention gating module The convolution kernel size of the convolution layer, the second convolution layer, and the third convolution layer is all 1×1; the convolution kernel size of the first upsampling layer is 2×2; the first context attention module of the first The convolution kernel size of the convolutional layer, the second convolutional layer, and the third convolutional layer is all 3×3, and the padding is 1. The convolution kernel size of the fourth convolutional layer of the first contextual attention module is 1× 1; The convolution kernel size of the first convolutional layer of the decoder is 1×1.

In one embodiment of the present invention, in step g), the Dice loss and the cross-entropy loss are summed to obtain the total loss, and the Adam optimizer is used to train the segmentation network model using the total loss to obtain the optimized segmentation network model. During training, batches The size is set to 32, the iteration period is set to 200, and the learning rate is set to 0.001.

Finally, it should be noted that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, it is still The technical solutions described in the foregoing embodiments may be modified, or some of the technical features may be equivalently replaced. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims (9)

1. A method of cardiac MRI segmentation based on contextual cascade attention, comprising the steps of:

a) Collecting cardiac MRI data of n subjects to obtain MRI data sets s, s= { s ₁ ,s ₂ ,...,s _i ,...,s _n }，s _i Cardiac MRI data for the i-th subject, i e {1,2,., n };

b) Preprocessing the MRI data set s to obtain a preprocessed data set F, F= { F ₁ ,F ₂ ,...,F _i ,...,F _n }，F _i The i-th preprocessed two-dimensional image data;

c) Dividing the preprocessed data set F into a training set, a testing set and a verification set;

d) Establishing a segmentation network model formed by an encoder and a decoder;

e) The preprocessed two-dimensional image data F _i Input into encoder of dividing network model, and output to obtain characteristic diagramFeature map->Feature map->Feature map->

f) Map the characteristic mapFeature map->Feature map->Feature map->Input into decoder of segmentation network model, output to obtain predictive segmentation image>

g) Training a segmentation network model to obtain an optimized segmentation network model;

step e) comprises the steps of:

e-1) an encoder for dividing a network model is composed of a first residual initial module, a first maximum pooling layer, a second residual initial module, a second maximum pooling layer, a third residual initial module, a third maximum pooling layer and a fourth residual initial module;

e-2) the first residual error initial module is composed of a first branch, a second branch, a third branch, a fourth branch and a fifth branch, wherein the first branch is composed of a convolution layer, the second branch is sequentially composed of an average pooling layer and a convolution layer, the third branch is sequentially composed of a convolution layer and a BN layer, the fourth branch is sequentially composed of the first convolution layer, the second convolution layer and the BN layer, the fifth branch is sequentially composed of the first convolution layer, the second convolution layer, the first BN layer, the third convolution layer and the second BN layer, and the preprocessed two-dimensional image data F is obtained by _i Input into the first branch, output to obtain a feature mapThe preprocessed two-dimensional image data F _i Input into the second branch, output the obtained feature map +.>The preprocessed two-dimensional image data F _i Input into the third branch, output to obtain a feature mapThe preprocessed two-dimensional image data F _i Input into the fourth branch, output the obtained feature map +.>The preprocessed two-dimensional image data F _i Input into the fifth branch, output the obtained feature map +.>Feature map +.>Feature map->Feature map->Feature map->Performing splicing operation to obtain characteristic diagram->Feature map +.>And (4) feature map>The addition operation results in a feature map->

e-3) mapping the featuresInput into the first maximum pooling layer, and output to obtain characteristic diagram +.>

e-4) a second residual error initial module is composed of a first branch, a second branch, a third branch, a fourth branch and a fifth branch, wherein the first branch is composed of a convolution layer, the second branch is sequentially composed of an average pooling layer and a convolution layer, the third branch is sequentially composed of a convolution layer and a BN layer, the fourth branch is sequentially composed of a first convolution layer, a second convolution layer and a BN layer, the fifth branch is sequentially composed of the first convolution layer, the second convolution layer, the first BN layer, the third convolution layer and the second BN layer, and the characteristic diagram is formed by Input into the first branchOutputting the obtained characteristic diagram->Feature map +.>Input into the second branch, output the obtained feature map +.>Feature map +.>Input into the third branch, output the obtained feature map +.>Feature map +.>Input into the fourth branch, output the obtained feature map +.>Feature map +.>Input into the fifth branch, output the obtained feature map +.>Feature map +.>Feature mapFeature map->Feature map->Performing splicing operation to obtain characteristic diagram->Feature map +.>And feature mapThe addition operation results in a feature map->

e-5) mapping the featuresInputting into the second maximum pooling layer, outputting to obtain characteristic diagram +.>

e-6) a third residual error initial module is composed of a first branch, a second branch, a third branch, a fourth branch and a fifth branch, wherein the first branch is composed of a convolution layer, the second branch is sequentially composed of an average pooling layer and a convolution layer, the third branch is sequentially composed of a convolution layer and a BN layer, the fourth branch is sequentially composed of a first convolution layer, a second convolution layer and a BN layer, the fifth branch is sequentially composed of the first convolution layer, the second convolution layer, the first BN layer, the third convolution layer and the second BN layer, and the characteristic diagram is formed byInput into the first branch, output the obtained feature map +.>Feature map +. >Input into the second branch, output the obtained feature map +.>Feature map +.>Input into the third branch, output the obtained feature map +.>Feature map +.>Input into the fourth branch, output the obtained feature map +.>Feature map +.>Input into the fifth branch, output the obtained feature map +.>Feature map +.>Feature mapFeature map->Feature map->Performing splicing operation to obtain characteristic diagram->Feature map +.>And feature mapThe addition operation results in a feature map->

e-7) mapping the featuresInputting into the third maximum pooling layer, outputting to obtain characteristic diagram +.>

e-8) a fourth residual error initial module is composed of a first branch, a second branch, a third branch, a fourth branch and a fifth branch, wherein the first branch is composed of a convolution layer, the second branch is sequentially composed of an average pooling layer and a convolution layer, the third branch is sequentially composed of a convolution layer and a BN layer, the fourth branch is sequentially composed of a first convolution layer, a second convolution layer and a BN layer, the fifth branch is sequentially composed of the first convolution layer, the second convolution layer, the first BN layer, the third convolution layer and the second BN layer, and the characteristic diagram is formed byInput into the first branch, output the obtained feature map +.>Feature map +.>Input into the second branch, output the obtained feature map +.>Feature map +. >Input into the third branch, output the obtained feature map +.>Feature map +.>Input into the fourth branch, output the obtained feature map +.>Feature map +.>Input into the fifth branch, output the obtained feature map +.>Feature map +.>Feature mapFeature map->Feature map->Performing splicingThe join operation gets a feature map->Feature map +.>And feature mapThe addition operation results in a feature map->

2. The contextual cascade attention-based cardiac MRI segmentation method according to claim 1, wherein: from ACDC2017 public data in step a), cardiac MRI data of n subjects containing LV, RV, MYO structures were collected, resulting in MRI dataset s.

3. The contextual cascade attention-based cardiac MRI segmentation method according to claim 1, wherein: n=100 in step a).

4. The method of contextual cascade attention-based cardiac MRI segmentation according to claim 1, wherein step b) comprises the steps of:

b-1) cardiac MRI data s for the ith subject _i Resampling is carried out on the z-axis one by one, wherein the resampling is that the pixel pitch in the x-axis direction is 1.5, and the pixel pitch in the y-axis direction is 1.5;

b-2) resampling cardiac MRI data s _i Performing 2D center clipping operation with clipping size 224×224 to obtain clipped data F _i ' cutting the cut data F _i ' normalization processing is carried out to obtain preprocessed two-dimensional image data F _i 。

5. The contextual cascade attention-based cardiac MRI segmentation method according to claim 1, wherein: in the step c), the preprocessed data set F is divided into a training set, a testing set and a verification set according to the proportion of 7:2:1.

6. The contextual cascade attention-based cardiac MRI segmentation method according to claim 1, wherein: in the step e-2), the convolution kernel size of the convolution layer of the first branch is 1×1, the convolution kernel size of the convolution layer of the second branch is 1×1, the convolution kernel size of the convolution layer of the third branch is 1×1, the convolution kernel size of the first convolution layer of the fourth branch is 1×1, the convolution kernel size of the second convolution layer is 5×5, the packing is 2, the convolution kernel size of the first convolution layer of the fifth branch is 1×1, the convolution kernel size of the second convolution layer is 3×3, and the convolution kernel size of the third convolution layer is 3×3; in the step e-4), the convolution kernel size of the convolution layer of the first branch is 1×1, the convolution kernel size of the convolution layer of the second branch is 1×1, the convolution kernel size of the convolution layer of the third branch is 1×1, the convolution kernel size of the first convolution layer of the fourth branch is 1×1, the convolution kernel size of the second convolution layer is 5×5, the packing is 2, the convolution kernel size of the first convolution layer of the fifth branch is 1×1, the convolution kernel size of the second convolution layer is 3×3, and the convolution kernel size of the third convolution layer is 3×3; in the step e-6), the convolution kernel size of the convolution layer of the first branch is 1×1, the convolution kernel size of the convolution layer of the second branch is 1×1, the convolution kernel size of the convolution layer of the third branch is 1×1, the convolution kernel size of the first convolution layer of the fourth branch is 1×1, the convolution kernel size of the second convolution layer is 5×5, the packing is 2, the convolution kernel size of the first convolution layer of the fifth branch is 1×1, the convolution kernel size of the second convolution layer is 3×3, and the convolution kernel size of the third convolution layer is 3×3; in the step e-8), the convolution kernel size of the convolution layer of the first branch is 1×1, the convolution kernel size of the convolution layer of the second branch is 1×1, the convolution kernel size of the convolution layer of the third branch is 1×1, the convolution kernel size of the first convolution layer of the fourth branch is 1×1, the convolution kernel size of the second convolution layer is 5×5, the packing is 2, the convolution kernel size of the first convolution layer of the fifth branch is 1×1, the convolution kernel size of the second convolution layer is 3×3, and the convolution kernel size of the third convolution layer is 3×3; the convolution kernel size of the first maximum pooling layer in step e-3) is 2 x 2; the convolution kernel size of the second largest pooling layer in step e-5) is 2 x 2; the convolution kernel size of the third largest pooling layer in step e-7) is 2 x 2.

7. The method of contextual cascade attention-based cardiac MRI segmentation according to claim 1, wherein step f) comprises the steps of:

f-1) the decoder of the split network model is composed of Conv-block1, a first attention gating module, a first upsampling layer, a first context attention module, a first convolution layer, conv-block2, a second attention gating module, a second upsampling layer, a second context attention module, a second convolution layer, conv-block3, a third attention gating module, a third upsampling layer, a third context attention module, a third convolution layer, conv-block4, a fourth attention gating module, a fourth context attention module and a fourth convolution layer;

f-2) Conv-block4 is composed of a convolution layer, a BatchNorm layer and a ReLU activation function in sequence, and is characterized in thatInput into Conv-block4, and output to obtain characteristic diagram +.>The fourth attention gating module consists of a first convolution layer, a first BN layer, a second convolution layer, a second BN layer, a ReLU activation function, a third convolution layer, a third BN layer and a sigmoid function, and maps the characteristicsSequentially inputting into a first convolution layer and a first BN layer of a fourth attention gating module, and outputting to obtain a characteristic diagram ++ >Feature map +.>Sequentially inputting into a second convolution layer and a second BN layer of the fourth attention gate module, and outputting to obtain a feature mapFeature map +.>And (4) feature map>Adding to obtain a feature map->Feature map +.>Sequentially inputting into a ReLU activation function, a third convolution layer, a third BN layer and a sigmoid function of a fourth attention gating module, and outputting to obtain a feature map +.>Feature map +.>And (4) feature map>Multiplication to obtain a feature map->The fourth context attention module consists of a first convolution layer, a second convolution layer, a global maximum pooling layer, a third convolution layer, a fourth convolution layer and a sigmoid function, and is used for adding a characteristic diagram->Sequentially inputting the images into a first convolution layer and a second convolution layer of a fourth context attention module, and outputting to obtain a characteristic diagramFeature map +.>Input into the global maximum pooling layer of the fourth context attention module, and output to obtain a feature mapFeature map +.>Sequentially inputting into a third convolution layer and a fourth convolution layer of a fourth context attention module, and outputting to obtain a characteristic diagram ++>Feature map +.>And (4) feature map>Multiplication to obtain a feature map->Feature map +.>And (4) feature map>Adding to obtain a feature map->Feature map +.>Inputting into the sigmoid function of the fourth context attention module, outputting the obtained feature map +. >Feature map +.>Inputting into a fourth convolution layer to obtain a feature map +.>

f-3) Conv-block3 is composed of a convolution layer, a BatchNorm layer and a ReLU activation function in sequence, and is characterized in thatInput into Conv-block3, and output to obtain characteristic diagram +.>Feature map +.>Input into the third upsampling layer, output to get the feature map +.>The third attention gating module consists of a first convolution layer, a first BN layer, a second convolution layer, a second BN layer, a ReLU activation function, a third convolution layer, a third BN layer and a sigmoid function, and is used for decoding a characteristic diagram->Sequentially input to a third attention gating moduleIn the first convolution layer and the first BN layer, the obtained characteristic diagram is output>Feature map +.>Sequentially inputting into a second convolution layer and a second BN layer of a third attention gate control module, and outputting to obtain a characteristic diagram +.>Feature map +.>And feature mapAdding to obtain a feature map->Feature map +.>Sequentially inputting into a ReLU activation function, a third convolution layer, a third BN layer and a sigmoid function of a third attention gating module, and outputting to obtain a feature map +.>Feature map +.>And (4) feature map>Multiplication to obtain a feature map->Feature map +.>And (4) feature map>Cascading get feature map->The third context attention module consists of a first convolution layer, a second convolution layer, a global maximum pooling layer, a third convolution layer, a fourth convolution layer and a sigmoid function, and is used for adding a characteristic diagram- >Sequentially inputting into the first convolution layer and the second convolution layer of the third context attention module, and outputting to obtain a characteristic diagram ++>Feature map +.>Input into the global maximum pooling layer of the third contextual attention module, output the resulting feature map +.>Feature map +.>Sequentially inputting into a third convolution layer and a fourth convolution layer of a third context attention module, and outputting to obtain a characteristic diagram ++>Feature map +.>And (4) feature map>Multiplication to obtain a feature map->Feature map +.>And (4) feature map>Adding to obtain a feature map->Feature map +.>Inputting into the sigmoid function of the third context attention module, outputting the obtained feature map +.>Feature map +.>Inputting into the third convolution layer to obtain a feature map +.>

f-4) Conv-block2 is composed of a convolution layer, a BatchNorm layer and a ReLU activation function in sequence, and is characterized byInput into Conv-block2, and output to obtain feature map +.>Feature map +.>Input into the second upsampling layer, output to get the feature map +.>The second attention gating module consists of a first convolution layer, a first BN layer, a second convolution layer, a second BN layer, a ReLU activation function, a third convolution layer, a third BN layer and a sigmoid function, and is used for decoding a characteristic diagram->Sequentially inputting into a first convolution layer and a first BN layer of a second attention gating module, and outputting to obtain a characteristic diagram ++ >Feature map +.>Sequentially inputting into a second convolution layer and a second BN layer of a second attention gate control module, and outputting to obtain a characteristic diagram +.>Feature map +.>And feature mapAdding to obtain a feature map->Feature map +.>In turnInputting into a ReLU activation function, a third convolution layer, a third BN layer and a sigmoid function of the second attention gating module, and outputting to obtain a feature map +.>Feature map +.>And feature mapMultiplication to obtain a feature map->Feature map +.>And (4) feature map>Cascading get feature map->The second context attention module consists of a first convolution layer, a second convolution layer, a global maximum pooling layer, a third convolution layer, a fourth convolution layer and a sigmoid function, and is used for adding a characteristic diagram->Sequentially inputting into a first convolution layer and a second convolution layer of a second context attention module, and outputting to obtain a characteristic diagram ++>Feature map +.>Global maximum input to the second contextual attention moduleIn the pooling layer, the characteristic diagram is obtained by outputting>Feature map +.>Sequentially inputting into a third convolution layer and a fourth convolution layer of the second context attention module, and outputting to obtain a characteristic diagram ++>Feature map +.>And (4) feature map>Multiplication to obtain a feature map->Feature map +.>And (4) feature map>Adding to obtain a feature map- >Feature map +.>Inputting into the sigmoid function of the second context attention module, outputting the obtained feature map +.>Feature map +.>Inputting the first convolution layer to obtain a characteristic diagram +.>

f-5) Conv-block1 is composed of a convolution layer, a BatchNorm layer and a ReLU activation function in sequence, and is characterized in thatInput into Conv-block1, and output to obtain characteristic diagram +.>Feature map +.>Input into the first upsampling layer, output to get the feature map +.>The first attention gating module consists of a first convolution layer, a first BN layer, a second convolution layer, a second BN layer, a ReLU activation function, a third convolution layer, a third BN layer and a sigmoid function, and is used for decoding a characteristic diagram->Sequentially inputting into a first convolution layer and a first BN layer of a first attention gate control module, and outputting to obtain a characteristic diagram ++>Feature map +.>Sequentially inputting into a second convolution layer and a second BN layer of the first attention gating module, and outputting to obtain a characteristic diagram ++>Feature map +.>And feature mapAdding to obtain a feature map->Feature map +.>Sequentially inputting into a ReLU activation function, a third convolution layer, a third BN layer and a sigmoid function of the first attention gating module, and outputting to obtain a feature map +.>Feature map +.>And (4) feature map>Multiplication to obtain a feature map->Feature map +. >And (4) feature map>Cascading get feature map->First contextual attention modelThe block is composed of a first convolution layer, a second convolution layer, a global maximum pooling layer, a third convolution layer, a fourth convolution layer and a sigmoid function, and the feature map is->Sequentially inputting into a first convolution layer and a second convolution layer of a first context attention module, and outputting to obtain a characteristic diagram ++>Feature map +.>Input into the global maximum pooling layer of the first contextual attention module, output the resulting feature map +.>Feature map +.>Sequentially inputting into a third convolution layer and a fourth convolution layer of the first context attention module, and outputting to obtain a characteristic diagram ++>Feature map +.>And (4) feature map>Multiplication to obtain a feature mapFeature map +.>And (4) feature map>Adding to obtain a feature map->Feature map +.>Inputting into the sigmoid function of the first context attention module, outputting the obtained feature map +.>Feature map +.>Inputting into the first convolution layer to obtain a feature map +.>

f-6) mapping the featuresFeature map->Feature map->Feature map->Residual addition is carried out to obtain a characteristic diagram->

8. The contextual cascade attention-based cardiac MRI segmentation method according to claim 7, wherein: the convolution kernel size of the convolution layer of Conv-block4 in step f-2) is 3×3, and padding is 1; the convolution kernel sizes of the first convolution layer, the second convolution layer and the third convolution layer of the fourth attention gating module are all 1 multiplied by 1; the convolution kernel sizes of the first convolution layer, the second convolution layer and the third convolution layer of the fourth context attention module are 3×3, the padding is 1, and the convolution kernel size of the fourth convolution layer of the fourth context attention module is 1×1; the convolution kernel size of the fourth convolution layer of the decoder is 1×1; the convolution kernel size of the convolution layer of Conv-block3 in step f-3) is 3×3, and padding is 1; the convolution kernel sizes of the first convolution layer, the second convolution layer and the third convolution layer of the third attention gating module are all 1 multiplied by 1; the convolution kernel size of the third upsampling layer is 2×2; the convolution kernel sizes of the first convolution layer, the second convolution layer and the third convolution layer of the third context attention module are 3×3, the padding is 1, and the convolution kernel size of the fourth convolution layer of the third context attention module is 1×1; the convolution kernel size of the third convolution layer of the decoder is 1×1; f-4) the convolution kernel size of the convolution layer of Conv-block2 is 3×3, and padding is 1; the convolution kernel sizes of the first convolution layer, the second convolution layer and the third convolution layer of the second attention gating module are all 1 multiplied by 1; the convolution kernel size of the second upsampling layer is 2 x 2; the convolution kernel sizes of the first convolution layer, the second convolution layer and the third convolution layer of the second context attention module are all 3×3, the padding is 1, and the convolution kernel size of the fourth convolution layer of the second context attention module is 1×1; the convolution kernel size of the second convolution layer of the decoder is 1×1; f-5) the convolution kernel size of the convolution layer of Conv-block1 is 3×3, and padding is 1; the convolution kernel sizes of the first convolution layer, the second convolution layer and the third convolution layer of the first attention gating module are all 1 multiplied by 1; the convolution kernel size of the first upsampling layer is 2 x 2; the convolution kernel sizes of the first convolution layer, the second convolution layer and the third convolution layer of the first context attention module are all 3×3, the padding is 1, and the convolution kernel size of the fourth convolution layer of the first context attention module is 1×1; the convolution kernel size of the first convolution layer of the decoder is 1 x 1.

9. The contextual cascade attention-based cardiac MRI segmentation method according to claim 1, wherein: and g) summing the Dice loss and the cross entropy loss to obtain total loss, training the segmentation network model by using the Adam optimizer to obtain an optimized segmentation network model, wherein the batch size during training is set to be 32, the iteration period is set to be 200, and the learning rate is set to be 0.001.