Distributed medical image classification method

Abstract

The invention discloses a distributed medical image classification method. The method comprises the following steps: acquiring a medical image of each branch center and preprocessing the medical image; inputting the preprocessed medical image into a trained image parameter feature extractor for processing to obtain image parameter features; classifying the medical image into a corresponding image parameter category based on the image parameter feature, and then converting the medical image into a coordinated image based on a trained image coordinator corresponding to the image parameter category; inputting the coordinated image into a trained feature map extractor for conversion to obtain a feature map; and inputting the feature map into a trained classification model for processing to obtain a classification result of the medical image. According to the method, corresponding image coordinators are trained for different image parameter categories, so that feature distribution of various images is coordinated, and the generalization ability of the model is enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of artificial intelligence and medical image analysis, and in particular relates to a distributed medical image classification method. Background Art

[0002] Advanced medical image classification methods can extract key information from medical images and solve traditionally difficult problems for specific clinical problems. They have broad application prospects and important clinical value. In recent years, the field of medical artificial intelligence has paid more and more attention to the patient privacy and security issues and data distribution differences in multi-center applications. For the former, distributed models have emerged, which allow joint learning without sharing original data, thereby protecting patient privacy and reducing the risk of data leakage. For example, Federated Learning, as an emerging distributed machine learning method, allows multiple institutions to train models on local data and then send the trained model parameters to a central server for aggregation. This method not only retains the locality of the data, but also achieves global optimization of the model. By introducing distributed models, medical institutions are expected to overcome the privacy and security issues and data island effects in traditional centralized learning methods, and achieve larger-scale data integration and analysis while ensuring data security, thereby promoting cross-institutional collaborative research and accelerating innovation and progress in the field of medical artificial intelligence.

[0003] However, the distributed model cannot completely solve the problem of data distribution differences between multiple centers. Studies have shown that the performance of medical image classification models will be affected by imaging parameters such as hardware configuration and software algorithms, thereby increasing the risk of model overfitting. In response to the problem that medical images are affected by slice thickness, pixel size, noise, reconstruction algorithm, detector accuracy and other imaging parameters, researchers currently mainly adopt the following strategies to improve the stability of the output results of medical image classification models: 1) Resampling operation: resample the scanned image before feature extraction to reduce the differences in slice thickness and pixel size between different samples. However, conventional upsampling algorithms have limited capabilities, excessive upsampling will produce obvious artifacts, and downsampling will lose image detail information. Some researchers combine image resampling with Butterworth filters for preprocessing to correct the impact of pixel size changes, but Butterworth filters also blur the image, resulting in the loss of image details required for imaging omics. 2) Eigenvalue normalization: ComBat method and Z-score method are commonly used eigenvalue correction methods. The ComBat method can readjust the feature distribution in the test set and improve the verification accuracy of the imaging omics model. The Z-score method corrects the feature value by calculating the mean and standard deviation of each feature in each data set. 3) Stable feature screening: Improve the generalization performance of the model by screening out a stable feature set under different imaging parameters. However, the method of evaluating features one by one is inefficient and difficult to provide a direct reference for the subsequent development of new features and models. This problem is particularly evident when developing deep learning networks for direct prediction. Moreover, the screening process actually reduces the feature space that is potentially related to the prediction target to a certain extent, which has a negative impact on the training of high-precision models.

[0004] Therefore, in order to solve the problem that existing medical image classification methods are difficult to deal with data distribution differences while protecting patient privacy, it is urgent to propose a distributed medical image classification method based on the imaging parameter characteristics of medical images and the difficulties in data processing. Summary of the invention

[0005] In order to solve the above technical problems, the present invention proposes a distributed medical image classification method, which provides a basis for building a classification model with stable performance in multiple centers to solve the problems existing in the above-mentioned prior art.

[0006] To achieve the above object, the present invention provides a distributed medical image classification method, comprising the following steps:

[0007] The medical images of each sub-center server are input into the trained image parameter feature extractor for processing to obtain image parameter features;

[0008] classifying the medical image into a corresponding image parameter category based on the image parameter feature, and then converting the medical image into a coordinated image based on a trained image coordinator corresponding to the image parameter category;

[0009] Inputting the coordinated image into a trained feature map extractor for conversion to obtain a feature map;

[0010] The feature map is input into the trained classification model for processing, and the classification result of the medical image is obtained and aggregated.

[0011] Optionally, before the medical image of each sub-center server is input into the trained image parameter feature extractor for processing to obtain the image parameter feature, the method further includes:

[0012] Based on an interpolation algorithm, the pixel sizes of the medical image in three directions, namely, the x-axis, the y-axis, and the z-axis, are adjusted to fixed values, and the pixel intensity of the medical image is adjusted to a fixed range.

[0013] Optionally, the method for obtaining a trained image parameter feature extractor includes: constructing an image parameter feature extractor based on a three-dimensional convolutional neural network and a multi-layer perceptron, collecting medical images and corresponding imaging parameters from multiple sub-centers to form an image parameter feature extractor training sample set; training the image parameter feature extractor based on the image parameter feature extractor training sample set; and adjusting the parameters of the image parameter feature extractor based on the infoNCE loss function until the training end condition is met, thereby obtaining a trained image parameter feature extractor.

[0014] Optionally, the process of classifying the medical image into corresponding image parameter categories based on the image parameter characteristics includes: in each sub-center server, calculating the correlation between the image parameter characteristics of the medical image and the central image parameter characteristics of each image parameter category, and sorting them, and classifying the medical image into the image parameter category with the highest correlation.

[0015] Optionally, the process of acquiring the image parameter category includes: performing K-means clustering on the image parameter features, and taking each clustering cluster of the clustering result as the image parameter category.

[0016] Optionally, the process of acquiring the central image parameter feature includes: for each image parameter category, calculating the sum of correlations between each image feature parameter in each category and all other image parameter features, sorting them, and selecting the image parameter feature with the highest sum of correlations as the central image parameter feature of the corresponding image parameter category.

[0017] Optionally, the process of acquiring the trained image coordinator includes: constructing an image coordinator based on a three-dimensional convolutional neural network, and constructing an image coordination discriminator based on an image parameter feature extractor and a softmax layer; constructing an image coordinator training sample set based on medical images of image parameter categories corresponding to the image coordinator; acquiring image coordination target samples, and training the image coordinator and the image coordination discriminator respectively based on the image coordinator training sample set and the image coordination target samples until the number of training rounds is reached, aggregating the parameters of the final image coordinator and image coordination discriminator through a federated averaging algorithm, updating the parameters of the global image coordinator and the global image coordination discriminator, and obtaining the trained image coordinator.

[0018] Optionally, the process of obtaining image coordination target samples includes: selecting an image parameter category with the most medical images as an image coordination target initial sample; preprocessing the image coordination target initial sample, and inputting it into a trained image coordination target sample generator for processing to obtain an image coordination target sample.

[0019] Optionally, the process of acquiring the trained image coordination target sample generator includes: calculating the cosine similarity between the image parameter features of the image coordination target sample and the central image parameter features of each image parameter category, and taking the negative of the sum of the cosine similarities as the loss function value, until the loss function value meets the training end condition, to obtain the trained image coordination target sample generator.

[0020] Optionally, the trained feature map extractor is a three-dimensional convolutional neural network, and the end includes a convolutional layer with L1 regularization for generating multiple two-dimensional feature maps.

[0021] Optionally, the process of obtaining the trained classification model includes: constructing a classification model based on a convolutional neural network, a global average pooling layer, a multi-layer perceptron and a softmax layer; constructing a classification model training sample set based on the actual classification category corresponding to the medical image, training the classification model based on the classification model training sample set, and adjusting the parameters of the classification model based on the cross entropy loss function value; aggregating the parameters of the received classification model through a federated averaging algorithm, updating the parameters of the global classification model, and obtaining the trained classification model.

[0022] Compared with the prior art, the present invention has the following advantages and technical effects:

[0023] (1) The present invention can automatically classify medical images into corresponding image parameter categories by training the image parameter feature extractor. This process eliminates the reliance on manual input of image parameters and enables the system to recognize and process various imaging parameters on its own.

[0024] (2) The present invention converts medical images into coordinated images by training an image coordinator, so that the feature distributions of each image are aligned, reducing the distribution difference problem caused by different image sources, and improving the performance stability and consistency of the classification model in a multi-center environment. It is suitable for large-scale, multi-center medical image analysis tasks.

[0025] (3) The present invention uses a feature map extractor to convert the coordination image into a feature map, and uses a classification model to classify the feature map. This method avoids directly training a classification model with a huge parameter scale, greatly improving the training speed and resource utilization efficiency of the distributed medical image classification model. In addition, the separate design of the feature map extractor and the classification model enables the system to handle different medical image classification tasks more flexibly and adapt to various complex clinical needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0027] Figure 1 Schematic diagram of the framework of the distributed medical image classification method according to an embodiment of the present invention;

[0028] Figure 2 A flowchart of a training method for an image parameter feature extractor according to an embodiment of the present invention;

[0029] Figure 3 Schematic diagram of the training method of the feature map extractor according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0031] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0032] like Figure 1 As shown, this embodiment provides a distributed medical image classification method, which includes the following steps:

[0033] The medical images of each sub-center server are input into the trained image parameter feature extractor for processing to obtain image parameter features;

[0034] Classifying the medical image into a corresponding image parameter category based on the image parameter feature, and then converting the medical image into a coordinated image based on a trained image coordinator and a trained image coordination discriminator corresponding to the image parameter category;

[0035] Inputting the coordinated image into a trained feature map extractor for conversion to obtain a feature map;

[0036] The feature map is input into the trained classification model for processing, and the classification result of the medical image is obtained and aggregated.

[0037] As a specific embodiment, the medical image is three-dimensional medical image data obtained by scanning and reconstructing a certain medical imaging device such as CT, MRI, PET, etc.

[0038] The medical images of each sub-center server are input into the trained image parameter feature extractor for processing. Before obtaining the image parameter features, the medical images are also preprocessed. The preprocessing method is: using an interpolation algorithm to adjust the pixel size of the medical image in the three directions of the x-axis, y-axis, and z-axis to a fixed value, preferably, the fixed value is 1mm; adjusting the pixel intensity of the medical image to a fixed range, preferably, the fixed range is [-1,1].

[0039] The method of extracting image parameter features from medical images through an image parameter feature extractor is as follows: in each sub-center server, the medical image is input into the image parameter feature extractor, and after being processed by the image parameter feature extractor, a set of vectors is output as image parameter features.

[0040] The image parameter feature extractor is a combination of a three-dimensional convolutional neural network and a multi-layer perceptron. Preferably, the three-dimensional convolutional neural network uses 3D ResNet-34, the dimension of the output feature vector is 1024, the hidden layer dimension of the multi-layer perceptron is 2048, and the output dimension is 512.

[0041] like Figure 2 As shown, the training method of the image parameter feature extractor is:

[0042] Step A10, collecting 100 medical images from multiple sub-centers respectively, recording imaging parameters corresponding to the medical images, wherein the imaging parameters include pixel size, layer thickness, reconstruction algorithm, and device model, and obtaining a training sample set for an image parameter feature extractor;

[0043] Step A20, preprocessing the medical images of the image parameter feature extractor training sample set by using the “preprocessing the medical images” of the distributed medical image classification method;

[0044] Step A30, randomly selecting 16 training samples from each sub-center server, inputting the medical image into an image parameter feature extractor, and obtaining image parameter features of the medical image;

[0045] Step A40, transmitting the image parameter characteristics of the medical image and the corresponding imaging parameters to the central server;

[0046] Step A50, in the central server, for the image parameter features of two different medical images, the infoNCE loss function is used to evaluate the current performance of the image parameter feature extractor, and the calculation formula is:

[0047]

[0048] Among them, z i and z j The image parameter features representing medical images with the same imaging parameters, i.e., positive sample pairs; z k Represents z i All negative samples and z j ; τ is a positive temperature parameter; N is z i The number of negative samples plus 1. sim(A,B) is the cosine similarity function, and the calculation formula is:

[0049]

[0050] Wherein, A and B are two non-zero vectors; A·B represents the dot product of A and B; ||A|| and ||B|| are the Euclidean lengths of A and B, respectively. If the loss function value does not meet the training end condition, the parameters of the parameter feature extractor are adjusted, the adjusted parameters are transmitted to each sub-center server, and the process jumps to step A30 for iterative training until the loss function value meets the training end condition, thereby obtaining a trained parameter feature extractor.

[0051] The medical image is classified into a corresponding image parameter category based on the image parameter feature, and then the medical image is converted into a coordinated image based on the trained image coordinator and the trained image coordination discriminator corresponding to the image parameter category. The method of classifying the medical image into the corresponding image parameter category based on the image parameter feature is as follows: in each sub-center server, the correlation between the image parameter feature of the medical image and the central image parameter feature of each image parameter category is calculated. The correlation is measured by using the Euclidean distance to classify the medical image into the image parameter category with the highest correlation.

[0052] The method for obtaining the image parameter category is as follows: transmitting the image parameter features used for training the image parameter feature extractor in each sub-center to the central server; performing K-means clustering on the image parameter features in the central server; and taking each clustering cluster of the clustering result as the image parameter category.

[0053] The method for selecting the number of clusters for K-means clustering is as follows: using the elbow rule, calculate the total variation under different numbers of clusters, and select the point that significantly reduces the total variation as the candidate number of clusters; using the silhouette coefficient to evaluate the clustering effect under the candidate number of clusters, and select the number of clusters with the highest silhouette coefficient as the final number of clusters.

[0054] The method for obtaining the central image parameter feature is as follows: in the central server, for each image parameter category, the sum of the correlations between each image parameter feature in the category and all other image parameter features in the category is calculated, and the image parameter feature with the highest sum of correlations is selected as the central image parameter feature of the image parameter category.

[0055] The method for converting a medical image into a coordinated image based on the trained image coordinator and the trained image coordination discriminator corresponding to the image parameter category is as follows: selecting an image coordinator corresponding to the image parameter category of the medical image, inputting the medical image into the image coordinator, and outputting an image as a coordinated image after being processed by the image coordinator.

[0056] There are multiple image coordinators, and each image parameter category corresponds to an image coordinator.

[0057] The image coordinator is a three-dimensional convolutional neural network, and its end includes a convolutional layer for generating a coordinated image. Preferably, the three-dimensional convolutional neural network uses 3D ResNet-34.

[0058] The training method of the image coordinator is:

[0059] Step B10, determining the image parameter category corresponding to the image coordinator to be trained;

[0060] Step B20, collecting 50 medical images belonging to the image parameter category in each sub-center server to obtain an image coordinator training sample set; for a sub-center server that fails to collect a sufficient number of medical images, it is excluded from the training process of the image coordinator.

[0061] Step B30, in each sub-center server, pre-processing the medical images of the image coordinator training sample set by using the “pre-processing of medical images” of the distributed medical image classification method;

[0062] Step B40, randomly selecting 16 training samples from each sub-center server, inputting the medical images into the image coordinator, and obtaining a coordinated image of the medical image;

[0063] Step B50, in each sub-center server, input the coordination image to the image coordination discriminator to obtain a discrimination result;

[0064] Step B60, in the central server, inputting the image coordination target sample into the image coordination discriminator to obtain a discrimination result;

[0065] Step B70, in each sub-center server and the central server, calculate the discriminant loss function value of the image coordination discriminator. The training goal of the image coordination discriminator is to accurately distinguish which are the coordinated images generated from the image coordinator training samples and which are the image coordination target samples. According to the discriminant loss function value, adjust the parameters of the image coordination discriminator. The formula of the discriminant loss function is:

[0066]

[0067] Among them, x i represents the image coordination target sample, m represents the number of image coordination target samples, z j represents the image coordinator training sample, n represents the number of image coordinator training samples, D(·) is the image coordination discriminator, and G(·) is the image coordinator.

[0068] Step B80, in each sub-center server and the central server, calculate the generation loss function value of the image coordinator. The goal of the image coordinator is to deceive the image coordination discriminator into thinking that the coordinated image generated from the image coordinator training sample is the image coordination target sample. According to the generation loss function value, adjust the parameters of the image coordinator. The formula for the generation loss function is:

[0069]

[0070] Step B90, performing multiple rounds of local training in each sub-center server and the central server, and after each round of training, repeating steps B40 to E80 until a predetermined number of local training rounds is reached.

[0071] Step B100, transmitting the parameters of the image coordinator and the image coordination discriminator of each sub-center server to the central server;

[0072] Step B110: In the central server, the received parameters of the image coordinator and the image coordination discriminator are aggregated by a federated averaging algorithm to update the parameters of the global image coordinator and the global image coordination discriminator.

[0073] Step B120, distributing the updated parameters of the global image coordinator and the global image coordination discriminator to each sub-center server as the parameters of the image coordinator and the image coordination discriminator.

[0074] Step B130: If the sum of the discriminant loss function values ​​or the sum of the generated loss function values ​​of each sub-center does not meet the training end condition, and the number of training rounds does not reach the predetermined number, jump to step B40 for iterative training.

[0075] The structure of the image coordination discriminator is a combination of an image parameter feature extractor and a softmax layer, and its parameters are initialized using the parameters of the image parameter feature extractor, and are used to discriminate whether an input image is an image coordination target sample.

[0076] The method for obtaining the image coordination target sample is as follows: selecting an image parameter category with the most medical images, and using the medical images of this category as the image coordination target initial sample; transmitting the image coordination target initial sample to a central server; in the central server, preprocessing the image coordination target initial sample by the "preprocessing of medical images" of the distributed medical image classification method; in the central server, inputting the image coordination target initial sample into an image coordination target sample generator to obtain the image coordination target sample.

[0077] The structure of the image coordination target sample generator is the same as that of the image coordinator, which is a three-dimensional convolutional neural network, and the end of the neural network includes a convolutional layer for generating image coordination target samples.

[0078] The training method of the image coordination target sample generator is:

[0079] Step C10, transmitting the central image parameter features of each image parameter category to the central server;

[0080] Step C20, in the central server, inputting the preprocessed image coordination target initial sample into the image coordination target sample generator to obtain the image coordination target sample;

[0081] Step C30, in the central server, inputting the image coordination target sample into the image parameter feature extractor to obtain the image parameter feature of the image coordination target sample;

[0082] Step C40, in the central server, calculate the cosine similarity between the image parameter feature of the image coordination target sample and the central image parameter feature of each image parameter category, and use the negative of the sum of the cosine similarities as the loss function value. If the loss function value does not meet the training end condition, adjust the parameters of the image coordination target sample generator, and jump to step C20 for iterative training until the loss function value meets the training end condition, and obtain a trained image coordination target sample generator.

[0083] The method of converting the coordination image into a feature map by a feature map extractor is as follows: in each sub-center server, the coordination image is input into the feature map extractor, and after being processed by the feature map extractor, the feature map is output. The feature map extractor is a three-dimensional convolutional neural network, and its end includes a convolutional layer with L1 regularization for generating multiple two-dimensional feature maps.

[0084] like Figure 3 As shown, the training method of the feature map extractor is:

[0085] Step D10, combining the feature map extractor with the global average pooling layer, the multi-layer perceptron, and the softmax layer as a feature extraction initial classification network;

[0086] Step D20, in the central server, inputting the image coordination target sample into the feature extraction initial classification network to obtain the predicted classification category;

[0087] Step D30, in the central server, comparing the predicted classification category with the actual classification category and calculating the cross entropy loss function;

[0088] Step D40, in the central server, if the cross entropy loss function value does not meet the training end condition, adjust the parameters of the feature extraction initial classification network and jump to step D20 for iterative training until the cross entropy loss function value meets the training end condition, obtain the trained feature map extractor, and transmit it to each sub-center server.

[0089] The method of inputting the feature map into the trained classification model for processing to obtain the classification result of the medical image is as follows: in each sub-center server, the feature map is input into the classification model, and after being processed by the classification model, the predicted classification category is output. The classification model is a combination of a convolutional neural network and a global average pooling layer, a multi-layer perceptron, and a softmax layer, which is used to generate the predicted classification category. Preferably, the convolutional neural network uses Densenet-121.

[0090] The training method of the classification model is:

[0091] Step E10, collecting 50 medical images from multiple sub-centers respectively, recording the actual classification categories corresponding to the medical images, and obtaining a classification model training sample set;

[0092] Step E20, in each sub-center server, the medical images in the classification model training sample set are processed through the first step to the fifth step of the distributed medical image classification method to obtain a corresponding feature map;

[0093] Step E30, in each sub-center server, the feature map is input into the classification model to obtain the predicted classification category;

[0094] Step E40, in each sub-center server, the predicted classification category is compared with the actual classification category, a cross entropy loss function is calculated, and the parameters of the classification model are adjusted according to the cross entropy loss function value;

[0095] Step E50, performing multiple rounds of local training in each sub-center server, and after each round of training, repeating steps E30 to E40 until a predetermined number of local training rounds is reached.

[0096] Step E60, transmitting the parameters of the classification model of each sub-center server to the central server;

[0097] Step E70: In the central server, the received classification model parameters are aggregated by a federated averaging algorithm to update the parameters of the global classification model.

[0098] Step E80, distributing the updated parameters of the global classification model to each sub-center server as parameters of the classification model.

[0099] Step E90: If the sum of the cross entropy loss function values ​​of each sub-center does not meet the training end condition and the number of training rounds does not reach the predetermined number, jump to step E30 for iterative training.

[0100] Technical effects:

[0101] (1) The present invention can automatically classify medical images into corresponding image parameter categories by training an image parameter feature extractor. This process eliminates the reliance on manually input image parameters, allowing the system to identify and process various imaging parameters on its own. In addition, even if there are new image parameter types not included in the training data, the present invention can effectively handle them, thereby significantly improving the generalization and promotion capabilities of the classification model and adapting to more practical application scenarios.

[0102] (2) The present invention converts medical images into coordinated images by training an image coordinator, so that the feature distributions of each image are aligned, reducing the distribution difference problem caused by different image sources, and improving the performance stability and consistency of the classification model in a multi-center environment. It is suitable for large-scale, multi-center medical image analysis tasks.

[0103] (3) The present invention uses a feature map extractor to convert the coordination image into a feature map, and uses a classification model to classify the feature map. This method avoids directly training a classification model with a huge parameter scale, greatly improving the training speed and resource utilization efficiency of the distributed medical image classification model. In addition, the separate design of the feature map extractor and the classification model enables the system to handle different medical image classification tasks more flexibly and adapt to various complex clinical needs.

[0104] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A distributed medical image classification method, characterized in that: The following steps are involved: The medical images of each sub-center server are input into the trained image parameter feature extractor for processing to obtain image parameter features; classifying the medical image into a corresponding image parameter category based on the image parameter feature, and then converting the medical image into a coordinated image based on a trained image coordinator corresponding to the image parameter category; Inputting the coordinated image into a trained feature map extractor for conversion to obtain a feature map; The feature map is input into the trained classification model for processing, and the classification result of the medical image is obtained and aggregated.

2. The distributed medical image classification method according to claim 1, characterized in that: Before the medical image of each sub-center server is input into the trained image parameter feature extractor for processing to obtain the image parameter feature, the method further includes: Based on an interpolation algorithm, the pixel sizes of the medical image in three directions, namely, the x-axis, the y-axis, and the z-axis, are adjusted to fixed values, and the pixel intensity of the medical image is adjusted to a fixed range.

3. The distributed medical image classification method according to claim 1, characterized in that: The method for obtaining a trained image parameter feature extractor includes: constructing an image parameter feature extractor based on a three-dimensional convolutional neural network and a multi-layer perceptron, collecting medical images and corresponding imaging parameters from multiple sub-center servers to form an image parameter feature extractor training sample set; training the image parameter feature extractor based on the image parameter feature extractor training sample set; and adjusting the parameters of the image parameter feature extractor based on an infoNCE loss function until a training end condition is met, thereby obtaining a trained image parameter feature extractor.

4. The distributed medical image classification method according to claim 1, characterized in that: The process of classifying the medical image into the corresponding image parameter category based on the image parameter characteristics includes: in each sub-center server, calculating the correlation between the image parameter characteristics of the medical image and the central image parameter characteristics of each image parameter category, and sorting them, and classifying the medical image into the image parameter category with the highest correlation.

5. The distributed medical image classification method according to claim 4, characterized in that: The process of acquiring the image parameter category includes: performing K-means clustering on the image parameter features, and taking each clustering cluster of the clustering result as the image parameter category.

6. The distributed medical image classification method according to claim 4, characterized in that: The process of acquiring the central image parameter feature includes: for each image parameter category, calculating the sum of the correlations between each image feature parameter in each category and all other image parameter features, sorting them, and selecting the image parameter feature with the highest sum of correlations as the central image parameter feature of the corresponding image parameter category.

7. The distributed medical image classification method according to claim 1, characterized in that: The process of acquiring the trained image coordinator includes: constructing an image coordinator based on a three-dimensional convolutional neural network, and constructing an image coordination discriminator based on an image parameter feature extractor and a softmax layer; constructing an image coordinator training sample set based on medical images of image parameter categories corresponding to the image coordinator; acquiring image coordination target samples, and training the image coordinator and the image coordination discriminator respectively based on the image coordinator training sample set and the image coordination target samples until the number of training rounds is reached, aggregating the parameters of the final image coordinator and the image coordination discriminator through a federated averaging algorithm, updating the parameters of the global image coordinator and the global image coordination discriminator, and obtaining the trained image coordinator.

8. The distributed medical image classification method according to claim 7, characterized in that: The process of obtaining image coordination target samples includes: selecting image parameter categories with the most medical images as image coordination target initial samples; preprocessing the image coordination target initial samples, and inputting them into a trained image coordination target sample generator for processing to obtain image coordination target samples.

9. The distributed medical image classification method according to claim 8, characterized in that: The process of obtaining the trained image coordination target sample generator includes: calculating the cosine similarity between the image parameter features of the image coordination target sample and the central image parameter features of each image parameter category, and taking the negative of the sum of the cosine similarities as the loss function value until the loss function value meets the training end condition, thereby obtaining the trained image coordination target sample generator.

10. The distributed medical image classification method according to claim 1, characterized in that: The process of obtaining the trained classification model includes: constructing a classification model based on a convolutional neural network, a global average pooling layer, a multi-layer perceptron and a softmax layer; constructing a classification model training sample set based on the actual classification category corresponding to the medical image, training the classification model based on the classification model training sample set, and adjusting the parameters of the classification model based on the cross entropy loss function value; aggregating the parameters of the received classification model through a federated averaging algorithm, updating the parameters of the global classification model, and obtaining the trained classification model.

Images