CN117078941B

CN117078941B - Cardiac MRI segmentation method based on context cascade attention

Info

Publication number: CN117078941B
Application number: CN202311231297.8A
Authority: CN
Inventors: 刘瑞霞; 胡盼盼; 舒明雷; 刘照阳; 陈永健; 王�琦
Original assignee: Qilu University of Technology; Qingdao Hisense Medical Equipment Co Ltd; Shandong Institute of Artificial Intelligence
Current assignee: Qilu University of Technology; Qingdao Hisense Medical Equipment Co Ltd; Shandong Institute of Artificial Intelligence
Priority date: 2023-09-22
Filing date: 2023-09-22
Publication date: 2024-03-01
Anticipated expiration: 2043-09-22
Also published as: CN117078941A

Abstract

A heart MRI segmentation method based on context cascade attention relates to the technical field of medical image segmentation, and a residual error initial module is introduced into an encoder to better learn effective characteristic representation, so that the performance and generalization capability of a model are improved. The features of each layer are refined by concatenation operations with the complementary information of the different layers in the decoder, while the context information of each layer is explored by preserving local information and compressing global information using a context attention module, and salient features are highlighted by suppressing unimportant information areas, thereby improving the accuracy of segmentation.

Description

Cardiac MRI segmentation method based on context cascade attention

Technical Field

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

Background

The accurate segmentation of cardiac MRI is of great importance in the field of medical image processing, aimed at accurately extracting cardiac structures, such as ventricles, atria, cardiac muscles, etc., from cardiac MR images, to assist doctors in accurately diagnosing and treating cardiac diseases. At present, research methods for segmenting cardiac MR images are mainly divided into a traditional method and a deep learning method, wherein the traditional method is difficult to process complex cardiac structures in cardiac MRI segmentation, so that the segmentation effect is poor, and the deep learning method can better capture complex features in cardiac MR images. U-Net is used as a representative deep learning system architecture, an encoder-decoder structure is adopted, jump connection is introduced, the problem of information loss of a traditional convolutional neural network in segmentation tasks is solved, and important breakthroughs are brought for research and application of cardiac MRI segmentation. However, feature abstraction capability is insufficient and there is a lack of problem of learning context between pixels, which results in complexity of segmentation.

Disclosure of Invention

In order to overcome the deficiencies of the above techniques, the present invention provides a method of context-cascade attention-based cardiac MRI segmentation that better captures and represents complex data features.

The technical scheme adopted for overcoming the technical problems is as follows:

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 the segmentation network model to obtain an optimized segmentation network model.

Further, in step a), cardiac MRI data of n subjects containing LV, RV, MYO structures are collected from ACDC2017 public data, resulting in MRI dataset s.

Preferably, n=100 in step a).

Further, 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 。

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

Further, 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 +.>Will be pretreatedTwo-dimensional image data F _i Input into the third branch, output the obtained feature map +.>The 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 mapFeature map->Feature map->Performing splicing operation to obtain characteristic diagram->Feature map +.>And feature mapThe addition operation results in a feature map->e-3) mapping the features->Input 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, and 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, so that the characteristic diagram is obtained >Input into the first branch, output the obtained feature map +.>Feature map +.>Input into the second branch, output the obtained feature map +.>Map the characteristic mapInput 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 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-5) mapping the characteristic pattern->Inputting 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, and the third branch is sequentially composed of convolution layersThe 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 expressed by->Input 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 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-7) characterizing diagrams->Inputting 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, and 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, so that the characteristic diagram is obtained>Input 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 +.>Map the characteristic mapFeature map->Feature map->Feature map->Performing splicing operationObtaining a characteristic map->Map the characteristic mapAnd (4) feature map>The addition operation results in a feature map->Preferably, in step e-2), the convolution kernel size of the first branch is 1×1, the convolution kernel size of the second branch is 1×1, the convolution kernel size of the third branch is 1×01, the convolution kernel size of the first convolution layer of the fourth branch is 1×11, the convolution kernel size of the second convolution layer is 5×25, the padding is 2, the convolution kernel size of the first convolution layer of the fifth branch is 1×31, the convolution kernel size of the second convolution layer is 3×43, and the convolution kernel size of the third convolution layer is 3×53; in the step e-4), the convolution kernel size of the convolution layer of the first branch is 1×61, the convolution kernel size of the convolution layer of the second branch is 1×71, the convolution kernel size of the convolution layer of the third branch is 1×81, the convolution kernel size of the first convolution layer of the fourth branch is 1×91, 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 1×01, the convolution kernel size of the second convolution layer is 3×13, and the convolution kernel size of the third convolution layer is 3×23; in the step e-6), the convolution kernel size of the convolution layer of the first branch is 1×31, the convolution kernel size of the convolution layer of the second branch is 1×41, the convolution kernel size of the convolution layer of the third branch is 1×51, 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; step e-8) wherein 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 of the third branch The convolution kernel size of the layers 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 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.

Further, 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 that Input 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 is used for decoding a feature map->Sequentially inputting into a first convolution layer and a first BN layer of a fourth attention gate control module, and outputting to obtain a characteristic diagramFeature map +.>Sequentially inputting into a second convolution layer and a second BN layer of a fourth attention gating module, and outputting to obtain a characteristic diagram ++>Feature 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 conveyingThe first and second convolution layers of the fourth context attention module are input to output and obtain a characteristic diagram +.>Feature map +.>Input into the global maximum pooling layer of the fourth contextual attention module, output the resulting feature map +. >Feature 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->Map the characteristic mapAnd (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 mapf-3) Conv-block3 is composed of a convolution layer, a BatchNorm layer and a ReLU activation function in sequence, and a characteristic diagram is +.>Input 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 inputting into a first convolution layer and a first BN layer of a third attention gate control module, and outputting to obtain a characteristic diagram +.>Feature map +.>Sequentially input to a third attention gateIn the second convolution layer and the second BN layer of the module, a characteristic diagram is output and obtained>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->Third context attention module is composed of first convolution layer, second convolution layer and third convolution layerThe two convolution layers, the global maximum pooling layer, the third convolution layer, the fourth convolution layer and the sigmoid function constitute 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 a characteristic diagram is +. >Input 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 (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 the second attention gating module, and outputting to obtain a feature map +.>Map the characteristic mapAnd (4) feature map>Multiplication 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 +.>Input into the global maximization layer of the second contextual attention module, output the resulting feature map +.>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 a characteristic diagram is +.>Input 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 ++ >Map the characteristic mapAnd (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 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->The first 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 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 map->Feature 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 of the characteristics->Feature map->Feature map->Feature map->Residual addition is carried out to obtain a characteristic diagram->

Preferably, 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. Further, in step g), the Dice loss and the cross entropy loss are summed to obtain total loss, an Adam optimizer is used for training the segmentation network model by using the total loss to obtain an optimized segmentation network model, 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.

The beneficial effects of the invention are as follows: and a residual error initial module is introduced into the encoder to better learn effective characteristic representation, so that the performance and generalization capability of the model are improved. The features of each layer are refined by concatenation operations with the complementary information of the different layers in the decoder, while the context information of each layer is explored by preserving local information and compressing global information using a context attention module, and salient features are highlighted by suppressing unimportant information areas, thereby improving the accuracy of segmentation.

Drawings

FIG. 1 is a block diagram of a split network model of the present invention;

FIG. 2 is a block diagram of a residual initialization module of the present invention;

FIG. 3 is a block diagram of an attention gating module of the present invention;

fig. 4 is a block diagram of a contextual attention module of the present invention.

Detailed Description

The invention is further described with reference to fig. 1 to 4.

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 ith 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 Is the i-th preprocessed two-dimensional image data.

c) The preprocessed data set F is divided into a training set, a testing set and a verification set.

d) A partitioning network model is built consisting of an encoder and a decoder.

Complex data features are better captured and represented in the encoder using a residual initialization module, and features of multi-scale and multi-resolution spatial representation are learned in the decoder through multi-layer contextual concatenation operations.

In one embodiment of the invention, from ACDC2017 common data in step a), cardiac MRI data of n subjects containing LV, RV, MYO structures are collected, resulting in MRI dataset s. In this embodiment, preferably, n=100 in step a).

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

b-1) cardiac MRI data s for the ith subject _i The resampling is performed slice by slice along the z-axis with a pixel pitch of 1.5 in the x-axis direction and a pixel pitch of 1.5 in the y-axis direction.

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

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

In one embodiment of the invention, step e) comprises the steps of:

the e-1) encoder for dividing the 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 the obtained feature map +.>The 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 mapFeature map->Feature map->Performing splicing operation to obtain characteristic diagram->Feature map +.>And feature mapThe addition operation results in a feature map->e-3) mapping the features->Input 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, and 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, so that the characteristic diagram is obtained >Input into the first branch, output the obtained feature map +.>Feature map +.>Input into the second branch, output the obtained feature map +.>Map the characteristic mapInput 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 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-5) mapping the characteristic pattern->Inputting 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, and 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, so that the characteristic diagram is obtained>Input 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 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-7) characterizing diagrams->Inputting 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, and the fifth branch is sequentially composed of a first convolution layer, a second convolution layer and a third convolution layerA BN layer, a third convolution layer, a second BN layer, and a feature map +.>Input 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 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->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, the convolution kernel size of the convolution layer of the third branch is 1×01, the convolution kernel size of the first convolution layer of the fourth branch is 1×11, the convolution kernel size of the second convolution layer is 5×25, the padding is 2, the convolution kernel size of the first convolution layer of the fifth branch is 1×31, the convolution kernel size of the second convolution layer is 3×43, and the convolution kernel size of the third convolution layer is 3×53; in the step e-4), the convolution kernel size of the convolution layer of the first branch is 1×61, the convolution kernel size of the convolution layer of the second branch is 1×71, the convolution kernel size of the convolution layer of the third branch is 1×81, the convolution kernel size of the first convolution layer of the fourth branch is 1×91, 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 convolution layer of the first branch in step e-6) 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 1×1 The size of the convolution kernel of the first convolution layer of the fifth branch is 1 multiplied by 1, the convolution kernel of the second convolution layer is 3 multiplied by 03, and the convolution kernel of the third convolution layer is 3 multiplied by 13, which are 5 multiplied by 5, and padding is 2; in the step e-8), the convolution kernel size of the convolution layer of the first branch is 1×21, the convolution kernel size of the convolution layer of the second branch is 1×31, the convolution kernel size of the convolution layer of the third branch is 1×41, 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 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. In one embodiment of the invention, 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 is used for decoding a feature map->Sequentially inputting into a first convolution layer and a first BN layer of a fourth attention gate control module, and outputting to obtain a characteristic diagramFeature map +.>Sequentially inputting into a second convolution layer and a second BN layer of a fourth attention gating module, and outputting to obtain a characteristic diagram ++>Feature 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->Fourth context noteThe force intention 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 designing a characteristic diagram->Sequentially inputting into a first convolution layer and a second convolution layer of a fourth context attention module, and outputting to obtain a characteristic diagram +. >Feature map +.>Input into the global maximum pooling layer of the fourth contextual attention module, output the resulting feature map +.>Feature 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->Map the characteristic mapAnd (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 mapf-3) Conv-block3 is composed of a convolution layer, a BatchNorm layer and a ReLU activation function in sequence, and a characteristic diagram is +.>Input 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 inputting into a first convolution layer and a first BN layer of a third 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 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 mapFeature 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 a characteristic diagram is +.>Input 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 to be specificSyndrome/pattern of->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 (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 the second 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 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 +.>Input into the global maximization layer of the second contextual attention module, output the resulting feature map +.>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 mapFeature 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 a characteristic diagram is +.>Input 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 (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 the first attention gating module, and outputting to obtain a feature map +.>Map the characteristic mapAnd (4) feature map>Multiplication to obtain a feature map->Feature map +.>And (4) feature map>Cascading get feature map->The first 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 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 map->Feature 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 of the characteristics->Feature map->Feature map->Feature map->Residual addition is carried out to obtain a characteristic diagram->

In this embodiment, it is preferred that the convolution kernel size of the convolutions 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.

In one embodiment of the present invention, in step g), the Dice loss and the cross entropy loss are summed to obtain a total loss, and the Adam optimizer is used to train the segmentation network model by using the total loss to obtain an optimized segmentation network model, wherein the batch size during training is set to 32, the iteration cycle is set to 200, and the learning rate is set to 0.001.

Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

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

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

step e) comprises the steps of:

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:

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-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.