Tumor analysis method based on pathological tissue image

Abstract

The invention relates to the technical field of medical image processing, and particularly discloses a pathological tissue image-based tumor analysis method, which comprises the steps of data acquisition and preprocessing, network construction, image enhancement, adjacent layer feature fusion, image classification and knowledge distillation. According to the scheme, features are extracted from different levels by adopting an image enhancement and comparative learning method, the capability of extracting global features and capturing local details of the model is improved, and by calculating strong and weak enhancement difference loss, it is ensured that enhancement operation does not excessively change feature representation of the image, and overfitting of the model is prevented; features are extracted and fused from each layer of feature map of the teacher network through an attention mechanism, and the detail capturing ability of the model to a pathological image is enhanced; a knowledge distillation method is used, knowledge of a teacher network is introduced, and a student network not only pays attention to classification of hard tags, but also can capture a relative relationship between classes, so that the classification accuracy is improved, and the calculation resource demand of a model is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and in particular to a tumor analysis method based on pathological tissue images. Background Art

[0002] Pathological tissue image analysis is a key technology for cancer diagnosis. Cancer cells are round, oval, and in various irregular shapes, with different arrangements. Cancer cells and stroma show similar colors in pathological tissue images, showing complexity in both global and local features. General pathological tissue image processing methods have difficulty controlling the degree of processing, resulting in the loss of original information of image features, making it difficult for the model to correctly identify important structures or details in the image, thus affecting classification performance; general image classification models have insufficient representation capabilities for complex image structures, and cannot fully consider the weights and importance of features at different layers, resulting in the loss of key information; general network training methods rely only on real labels, especially when data is scarce, and are prone to overfitting. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a tumor analysis method based on pathological tissue images. In view of the problem that it is difficult to control the degree of processing in general pathological tissue image processing methods, resulting in the loss of original information of image features, making it difficult for the model to correctly identify important structures or details in the image, thereby affecting the classification performance, this solution adopts image enhancement and contrast learning methods to extract features from different levels, improve the model's ability to extract global features and capture local details, thereby improving the accuracy in pathological image classification tasks, and by calculating the difference loss between strong and weak enhancements, ensure that the enhancement operation does not excessively change the feature representation of the image, prevent the model from overfitting, and improve the discrimination ability and robustness of the classification model; in view of the general image classification model's insufficient ability to represent complex image structures, The problem of failure to fully consider the weights and importance of features at different layers, which leads to the loss of key information, is solved by extracting and fusing features from the feature maps of each layer of the teacher network through the attention mechanism, enhancing the model's ability to capture details of pathological images, ensuring that features of different scales can effectively participate in classification tasks, and providing more accurate multi-scale feature representations for subsequent classification. In view of the problem that general network training methods only rely on real labels, especially in the case of scarce data, overfitting is prone to occur. This solution uses the knowledge distillation method to introduce the knowledge of the teacher network. The student network not only focuses on the classification of hard labels, but also captures the relative relationship between classes, thereby improving the accuracy of classification. The calculation of the comprehensive loss function effectively improves the generalization ability of the student network and reduces the computing resource requirements of the model.

[0004] The technical solution adopted by the present invention is as follows: The present invention provides a tumor analysis method based on pathological tissue images, the method comprising the following steps:

[0005] Step S1: data collection and preprocessing, obtaining a dataset of annotated pathological tissue images of tumor tissue from a public database, and normalizing the pathological tissue images;

[0006] Step S2: Network construction: a teacher network and a student network are established based on a residual convolutional neural network. The teacher network is used to extract deep features of the image, and the student network is used to learn features.

[0007] Step S3: Image enhancement, using weak enhancement and strong enhancement to process the pathological tissue image, extracting the local features and global features of the pathological tissue image respectively, and establishing a contrastive learning model for optimizing the teacher network;

[0008] Step S4: Adjacent layer feature fusion, the features extracted from different layers of the teacher network are fused using local and global attention mechanisms to generate a feature map containing multi-scale information;

[0009] Step S5: Image classification, the teacher network classifies the feature map and completes the entire pathological image analysis and classification process;

[0010] Step S6: Knowledge distillation: the student network learns the deep features extracted by the teacher network and is trained. The trained student network is used to complete tumor category classification.

[0011] Furthermore, in step S3, the image enhancement specifically includes the following steps:

[0012] Step S31: applying a strong enhancement operation to the pathological tissue image to highlight the overall distribution of cells and generate a strong enhanced image;

[0013] Step S32: performing a weak enhancement operation on the pathological tissue image to highlight the cell shape and surrounding tissue structure, thereby generating a weakly enhanced image;

[0014] Step S33: extracting strong enhanced image features and weak enhanced image features from the strong enhanced image and the weak enhanced image respectively, taking the enhanced image as a positive sample of the original image, minimizing the distance between positive samples, taking other category images as negative samples, maximizing the distance between negative samples, and calculating global feature loss and local feature loss;

[0015] Step S34: strong and weak enhancement difference loss calculation, minimizing the feature distance between the strong enhanced image and the weak enhanced image and the original image, and retaining sufficient feature information of the enhanced image;

[0016] Step S35: Calculate the total loss using the following formula: ;

[0017] In the formula, represents the total loss function, represents the global feature loss function, represents the local feature loss function, represents the enhanced difference loss, Represents the weight parameters that control different loss terms.

[0018] Furthermore, in step S4, the adjacent layer feature fusion specifically includes the following steps:

[0019] Step S41: feature extraction, inputting the strongly enhanced image and the weakly enhanced image into the teacher network, and extracting attention features from each layer output of the teacher network;

[0020] Step S42: feature weighting, using the local attention mechanism to model the correlation between feature maps in each layer and generate weighted output features of each layer;

[0021] Step S43: self-attention feature fusion, using the global self-attention mechanism to fuse the weighted output features of each layer to capture detail features;

[0022] Step S44: Feature enhancement, dynamically adjust the weight of each feature, filter redundant and noisy information, and output a feature map that integrates multi-scale information.

[0023] Furthermore, in step S5, the image classification specifically includes the following steps:

[0024] Step S51: global average pooling calculation, using global average pooling to calculate the average value of all pixels in each feature map, and converting the high-dimensional feature map into a low-dimensional feature vector;

[0025] Step S52: setting a fully connected layer, inputting the low-dimensional feature vector into the fully connected layer, further learning the features of the image, and using a nonlinear activation function to enhance the expression ability of the model;

[0026] Step S53: adding a classifier, inputting the feature vector after the fully connected layer into the Softmax classifier, and outputting the probability of tumor classification;

[0027] Step S54: Model training, training the teacher network based on the contrastive learning model, adjusting the model parameters through back propagation to minimize the total loss.

[0028] Furthermore, in step S6, the knowledge distillation specifically includes the following steps:

[0029] Step S61: the teacher network transfers knowledge to the student network, using the tumor classification probability of the teacher network as a soft label, and the student network learns the teacher network and the soft label;

[0030] Step S62: Classification loss calculation, the student network classifies according to the true label, and uses the cross entropy loss function to calculate the difference between the predicted result and the true label;

[0031] Step S63: Distillation loss, calculating the difference between the student network output and the teacher network output as the distillation loss;

[0032] Step S64: feature matching loss, using L2 loss to calculate the difference between the feature maps of the teacher network and the student network at a specific level;

[0033] Step S65: The total loss function of the student network is calculated by combining the above loss items. The formula used is as follows: ;

[0034] In the formula, represents the total loss function of the student network, represents the classification loss, represents the distillation loss, represents the feature matching loss, , and is the weight parameter that controls different loss terms;

[0035] Step S66: Iterative training, using the back propagation algorithm to calculate the gradients of all loss functions in the student network relative to its parameters, and updating the weights of the student network through the optimization algorithm, and using the trained student network to classify the newly input pathological tissue images.

[0036] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0037] (1) In view of the problem that it is difficult to control the degree of processing in general pathological tissue image processing methods, resulting in the loss of original information of image features, making it difficult for the model to correctly identify important structures or details in the image, thus affecting the classification performance, this scheme adopts image enhancement and contrastive learning methods to extract features from different levels, improve the model's ability to extract global features and capture local details, thereby improving the accuracy in pathological image classification tasks. By calculating the difference loss between strong and weak enhancements, it ensures that the enhancement operation does not excessively change the feature representation of the image, prevents model overfitting, and improves the discrimination ability and robustness of the classification model.

[0038] (2) In view of the problem that general image classification models are unable to fully consider the weights and importance of features at different layers, resulting in the loss of key information, this solution extracts and fuses features from the feature maps of each layer of the teacher network through the attention mechanism, enhances the model's ability to capture details of pathological images, ensures that features of different scales can effectively participate in the classification task, and provides a more accurate multi-scale feature representation for subsequent classification.

[0039] (3) In view of the problem that general network training methods only rely on real labels, especially when data is scarce, they are prone to overfitting. This solution uses the knowledge distillation method to introduce the knowledge of the teacher network. The student network not only focuses on the classification of hard labels, but also captures the relative relationship between classes, thereby improving the classification accuracy. The calculation of the comprehensive loss function effectively improves the generalization ability of the student network and reduces the computing resource requirements of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A schematic diagram of a process of a tumor analysis method based on pathological tissue images proposed by the present invention;

[0041] Figure 2 A schematic diagram of the student network construction method proposed in the present invention.

[0042] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0044] Example 1, see Figure 1 The present invention provides a tumor analysis method based on pathological tissue images, the method comprising the following steps:

[0045] Step S1: data collection and preprocessing, obtaining a dataset of annotated pathological tissue images of tumor tissue from a public database, normalizing the pathological tissue images, and unifying the size of the pathological tissue images to 256×256;

[0046] Step S2: Network construction: a teacher network and a student network are established based on a residual convolutional neural network. The teacher network is used to extract deep features of the image, and the student network is used to learn features.

[0047] Step S3: Image enhancement, using weak enhancement and strong enhancement to process the pathological tissue image, extracting the local features and global features of the pathological tissue image respectively, and establishing a contrastive learning model for optimizing the teacher network;

[0048] Step S4: Adjacent layer feature fusion, the features extracted from different layers of the teacher network are fused using local and global attention mechanisms to generate the final features containing multi-scale information;

[0049] Step S5: Image classification, the teacher network classifies the feature map and completes the entire pathological image analysis and classification process;

[0050] Step S6: Knowledge distillation: the student network learns the deep features extracted by the teacher network and is trained. The trained student network is used to complete tumor category classification.

[0051] Example 2, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In step S2, the network is constructed, specifically including the following steps:

[0052] Step S21: Use the deep ResNet50 model to build the teacher network, input the pathological tissue image with a size of 256×256 in the input layer, build 4 convolutional layers, extract multi-scale features in each convolutional layer, add ReLU activation function and pooling layer, and retain the output features of each layer;

[0053] Step S22: Use a lightweight ResNet18 model to build a student network. Each layer of the student network learns the features from the corresponding level of the teacher network, imitates the feature extraction capability of the teacher network, and builds the same convolutional layer and pooling layer structure as the teacher network.

[0054] Example 3, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In step S3, image enhancement specifically includes the following steps:

[0055] Step S31: using a strong enhancement operation on the pathological tissue image to highlight the overall distribution of cells through rotation, large-scale cropping, and color perturbation to generate a strong enhanced image;

[0056] Step S32: translating the pathological tissue image and adding mild noise to highlight the cell shape and surrounding tissue structure to generate a weakly enhanced image;

[0057] Step S33: extracting strong enhanced image features and weak enhanced image features from the strong enhanced image and the weak enhanced image respectively, taking the enhanced image as the positive sample of the original image, minimizing the distance between the positive samples, taking other category images as negative samples, maximizing the distance between the negative samples, and calculating the global feature loss and the local feature loss. The specific steps are as follows:

[0058] Step S331: using cosine similarity to compare the original image features and the strongly enhanced image features;

[0059] Step S332: Calculate the global feature loss function, using the following formula: L G =-log exp(sim( Z x , Z s ) / τ) ∑ k=1 2N δ[k≠i]exp(sim( Z x , Z k ) / τ ) ;

[0060] In the formula, represents the global feature loss function, represents weakly enhanced image features, represents the original image features, represents the strong enhanced image features, Represents other category image features, represents a parameter used to adjust the sensitivity of the model to the similarity distribution, δ[k≠i] Indicated in Calculate the indicator function of negative samples when represents the cosine similarity, is the number of samples in a batch, represents the traversal variable of the sample, Indicates the index of the current sample;

[0061] Step S333: using cosine similarity to compare the original image features and the strongly enhanced image features;

[0062] Step S334: Calculate the local feature loss function, using the following formula: L W =-log exp(sim( Z x , Z w ) / τ) ∑ k=1 2N δ[k≠i]exp(sim( Z x , Z k ) / τ ) ;

[0063] In the formula, represents the local feature loss function, Represents weakly enhanced image features;

[0064] Step S34: Calculate the difference loss between strong and weak enhancement, minimize the feature distance between the strong and weak enhanced images and the original image, and retain sufficient feature information of the enhanced image. The formula used is as follows: ;

[0065] In the formula, represents the enhanced difference loss, represents a strongly enhanced image, represents a weakly enhanced image, represents the original image, represents the Euclidean distance, represents the feature extraction function of the image, represents the L2 norm;

[0066] Step S35: Calculate the total loss using the following formula: ;

[0067] In the formula, represents the total loss function, Represents the weight parameters that control different loss terms.

[0068] By performing the operations, the general pathological tissue image processing methods are difficult to control the degree of processing, resulting in the loss of original information of image features, making it difficult for the model to correctly identify important structures or details in the image, thereby affecting the classification performance. This solution uses image enhancement and contrastive learning methods to extract features from different levels, improve the model's ability to extract global features and capture local details, thereby improving the accuracy in pathological image classification tasks. By calculating the difference loss between strong and weak enhancements, it is ensured that the enhancement operation does not excessively change the feature representation of the image, prevent the model from overfitting, and improve the discrimination ability and robustness of the classification model.

[0069] Example 4, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In step S4, the adjacent layer features are fused, which specifically includes the following steps:

[0070] Step S41: feature extraction, inputting the strongly enhanced image and the weakly enhanced image into the teacher network, and extracting attention features from each layer output of the teacher network;

[0071] Step S42: feature weighting, using the local attention mechanism to model the correlation between feature maps in each layer, and generate weighted output features of each layer. The specific steps are as follows:

[0072] Step S421: Data generation, generating query values, key values, and output values ​​for the feature graph of each layer;

[0073] Step S422: Attention weight calculation, using the dot product operation to calculate the similarity between each query value and all keys, and using the softmax function to convert the dot product operation calculation result into a probability distribution to measure the importance of each key. The formula used is as follows: ;

[0074] In the formula, represents the target query value, Represents and references key values, Indicates the final selected output value after the target query value and the reference key value match. represents the attention weight, The dimension of the vector representing the reference key value, represents the normalization function, Represents a normalization operation;

[0075] Step S423: weighted output, selecting the most relevant key value according to the similarity, applying the attention weight to the output value, and generating a weighted output feature;

[0076] Step S43: Self-attention feature fusion, using the global self-attention mechanism to fuse the weighted output features of each layer to capture detail features. The specific steps are as follows:

[0077] Step S431: Data generation, generating query values, key values, and output values ​​for the feature graph of each layer;

[0078] Step S432: Attention weight calculation, calculating the similarity between each query value and all keys, and normalizing the similarity using the softmax function to obtain the attention weight;

[0079] Step S433: feature fusion, performing weighted fusion on feature maps of different layers to obtain multi-scale context information from different layers;

[0080] Step S44: Feature enhancement, dynamically adjust the weight of each feature, filter redundant and noisy information, and output a feature map that integrates multi-scale information.

[0081] By performing the operations described above, the general image classification model has insufficient ability to represent the complex structure of the image and cannot fully consider the weights and importance of features at different layers, resulting in the loss of key information. This solution extracts and fuses features from the feature maps of each layer of the teacher network through the attention mechanism, enhances the model's ability to capture details of pathological images, ensures that features of different scales can effectively participate in the classification task, and provides more accurate multi-scale feature representation for subsequent classification.

[0082] Example 5, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In step S5, image classification specifically includes the following steps:

[0083] Step S51: global average pooling calculation, using global average pooling to calculate the average value of all pixels in each feature map, and converting the high-dimensional feature map into a low-dimensional feature vector;

[0084] Step S52: setting a fully connected layer, inputting the low-dimensional feature vector into the fully connected layer, further learning the features of the image, and using a nonlinear activation function to enhance the expression ability of the model;

[0085] Step S53: adding a classifier, inputting the feature vector after the fully connected layer into the Softmax classifier, and outputting the probability of tumor classification;

[0086] Step S54: Model training, training the teacher network based on the contrastive learning model, adjusting the model parameters through back propagation to minimize the total loss.

[0087] Example 6, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In step S6, knowledge distillation specifically includes the following steps:

[0088] Step S61: the teacher network transfers knowledge to the student network, using the tumor classification probability of the teacher network as a soft label, and the student network learns the teacher network and the soft label;

[0089] Step S62: Classification loss calculation. The student network classifies according to the true label and uses the cross entropy loss function to calculate the difference between the predicted result and the true label, which is recorded as ;

[0090] Step S63: Distillation loss, calculate the difference between the student network output and the teacher network output as the distillation loss, the formula used is as follows: ;

[0091] In the formula, represents the distillation loss, is the output of the teacher network, is the output of the student network, Parameters for adjusting the smoothness of probability distribution;

[0092] Step S64: Feature matching loss, using L2 loss to calculate the difference between the feature maps of the teacher network and the student network at a specific level, the formula used is as follows: ;

[0093] In the formula, represents the feature matching loss, and Represents the teacher network and the student network The feature map of the layer, represents L2 distance;

[0094] Step S65: The total loss function of the student network is calculated by combining the above loss items. The formula used is as follows: ;

[0095] In the formula, represents the total loss function of the student network, , and is the weight parameter that controls different loss terms;

[0096] Step S66: Iterative training, using the back propagation algorithm to calculate the gradients of all loss functions in the student network relative to its parameters, and updating the weights of the student network through the optimization algorithm, and using the trained student network to classify the newly input pathological tissue images.

[0097] By performing the above operations, the general network training method only relies on the real label, especially when the data is scarce, which is prone to overfitting. This solution uses the knowledge distillation method to introduce the knowledge of the teacher network. The student network not only focuses on the classification of hard labels, but also captures the relative relationship between classes, thereby improving the classification accuracy. The calculation of the comprehensive loss function effectively improves the generalization ability of the student network and reduces the computing resource requirements of the model.

[0098] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0099] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0100] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A tumor analysis method based on pathological tissue images, characterized in that: The method comprises the following steps: Step S1: data collection and preprocessing, obtaining a dataset of annotated pathological tissue images of tumor tissue from a public database, and normalizing the pathological tissue images; Step S2: Network construction: a teacher network and a student network are established based on a residual convolutional neural network. The teacher network is used to extract deep features of the image, and the student network is used to learn features. Step S3: Image enhancement, using weak enhancement and strong enhancement to process the pathological tissue image, extracting the local features and global features of the pathological tissue image respectively, and establishing a contrastive learning model for optimizing the teacher network; Step S4: Adjacent layer feature fusion, the features extracted from different layers of the teacher network are fused using local and global attention mechanisms to generate a feature map containing multi-scale information; Step S5: Image classification, the teacher network classifies the feature map and completes the entire pathological image analysis and classification process; Step S6: Knowledge distillation: the student network learns the deep features extracted by the teacher network and is trained. The trained student network is used to complete tumor category classification.

2. The tumor analysis method based on pathological tissue images according to claim 1, characterized in that: In step S3, the image enhancement specifically includes the following steps: Step S31: applying a strong enhancement operation to the pathological tissue image to highlight the overall distribution of cells and generate a strong enhanced image; Step S32: performing a weak enhancement operation on the pathological tissue image to highlight the cell shape and surrounding tissue structure, thereby generating a weakly enhanced image; Step S33: extracting strong enhanced image features and weak enhanced image features from the strong enhanced image and the weak enhanced image respectively, taking the enhanced image as a positive sample of the original image, minimizing the distance between positive samples, taking other category images as negative samples, maximizing the distance between negative samples, and calculating global feature loss and local feature loss; Step S34: strong and weak enhancement difference loss calculation, minimizing the feature distance between the strong enhanced image and the weak enhanced image and the original image, and retaining sufficient feature information of the enhanced image; Step S35: Calculate the total loss using the following formula: ； In the formula, represents the total loss function, represents the global feature loss function, represents the local feature loss function, represents the enhanced difference loss, Represents the weight parameters that control different loss terms.

3. The tumor analysis method based on pathological tissue images according to claim 2, characterized in that: In step S4, the adjacent layer features are fused, specifically including the following steps: Step S41: feature extraction, inputting the strongly enhanced image and the weakly enhanced image into the teacher network, and extracting attention features from each layer output of the teacher network; Step S42: feature weighting, using the local attention mechanism to model the correlation between feature maps in each layer and generate weighted output features of each layer; Step S43: self-attention feature fusion, using the global self-attention mechanism to fuse the weighted output features of each layer to capture detail features; Step S44: Feature enhancement, dynamically adjust the weight of each feature, filter redundant and noisy information, and output a feature map that integrates multi-scale information.

4. The tumor analysis method based on pathological tissue images according to claim 3 is characterized in that: In step S5, the image classification specifically includes the following steps: Step S51: global average pooling calculation, using global average pooling to calculate the average value of all pixels in each feature map, and converting the high-dimensional feature map into a low-dimensional feature vector; Step S52: setting a fully connected layer, inputting the low-dimensional feature vector into the fully connected layer, further learning the features of the image, and using a nonlinear activation function to enhance the expression ability of the model; Step S53: adding a classifier, inputting the feature vector after the fully connected layer into the Softmax classifier, and outputting the probability of tumor classification; Step S54: Model training, training the teacher network based on the contrastive learning model, adjusting the model parameters through back propagation to minimize the total loss.

5. The tumor analysis method based on pathological tissue images according to claim 4, characterized in that: In step S6, the knowledge distillation specifically includes the following steps: Step S61: the teacher network transfers knowledge to the student network, using the tumor classification probability of the teacher network as a soft label, and the student network learns the teacher network and the soft label; Step S62: Classification loss calculation, the student network classifies according to the true label, and uses the cross entropy loss function to calculate the difference between the predicted result and the true label; Step S63: Distillation loss, calculating the difference between the student network output and the teacher network output as the distillation loss; Step S64: feature matching loss, using L2 loss to calculate the difference between the feature maps of the teacher network and the student network at a specific level; Step S65: The total loss function of the student network is calculated by combining the above loss items. The formula used is as follows: ； In the formula, represents the total loss function of the student network, represents the classification loss, represents the distillation loss, represents the feature matching loss, , and is the weight parameter that controls different loss terms; Step S66: Iterative training, using the back propagation algorithm to calculate the gradients of all loss functions in the student network relative to its parameters, and updating the weights of the student network through the optimization algorithm, and using the trained student network to classify the newly input pathological tissue images.

Images