CN113435607B - Disease screening method based on federal learning - Google Patents

Abstract

The invention discloses a disease screening method based on federal learning, which comprises the following steps: 1) Constructing a shared data set; 2) Pre-training; 3) Calculating an accuracy average value; 4) Calculating the data quantity; 5) And (5) convergence. The invention belongs to the technical field of federal learning and deep learning, in particular to a disease screening method based on federal learning, which combines knowledge of federal learning and deep learning, can more fully utilize data of various places and can efficiently and accurately diagnose diseases.

Description

Disease screening method based on federal learning

Technical Field

The invention belongs to the technical field of federal learning and deep learning, and particularly relates to a disease screening method based on federal learning.

Background

A medical image is an image reflecting the internal structure or function of an anatomical region, and is composed of a set of image elements, either pixels (2D) or voxels (3D). Medical images are characterized by discrete images produced by sampling or reconstruction that map values to different spatial locations. The number of pixels is used to describe medical imaging under a certain imaging device and is also an expression describing anatomical and functional details thereof. The specific values expressed by the pixels are determined by the imaging equipment, the imaging protocol, the image reconstruction and the post-processing. But sometimes each patient examines data even up to thousands of images, assuming that the disease is in a concentrated outbreak, more images. Diagnosis by a physician alone results in a slow efficiency. The federal learning is combined with the deep learning to process the image data, so that the data can be comprehensively utilized, the image can be rapidly analyzed, and the diagnosis is accurate.

The technology closest to the invention is as follows:

1. image classification algorithm based on deep learning: image classification is to distinguish different types of images according to semantic information of the images, and is an important basic problem in computer vision. In deep learning, a convolutional neural network (Convolution Neural Network, CNN) is mainly used for image classification, pixel information of an image is taken as input, feature extraction and high-level abstraction are carried out through convolution operation, and model output is directly the result of image recognition. Currently, the common image classification CNN networks include Lenet, alxnet, vgg series, resnet series, acceptance series, densenet series, google et, and the like. However, the method cannot comprehensively utilize the data of hospitals in all places to carry out comprehensive treatment, so that the accuracy is low and the performance is poor.

2. DeCoVNet networks are weak supervised learning algorithms. The method has a heavy practical significance under the conditions of uneven distribution of disease cases and small total quantity. The method has the characteristics of high operation speed and less requirement on solving the data label, but still has the defect of low accuracy so as to easily generate misdiagnosis.

Disclosure of Invention

Aiming at the situation, in order to overcome the defects of the prior art, the invention provides a disease screening method based on federal learning, which combines knowledge of federal learning and deep learning, can more fully utilize data of various places and can efficiently and accurately diagnose diseases.

The technical scheme adopted by the invention is as follows: the invention relates to a disease screening method based on federal learning, which comprises the following steps:

1) The server builds a shared data set and transmits an initial model (U-Net++, deCoVNet) to the participating training clients;

2) When a client runs a first epoch, performing pre-training on a U-Net++ model by using an unsupervised learning training to obtain a mask with a mark and a training set with the mark; obtaining masks of all training sets by the U-Net++ model after the training sets are pre-trained; the mask of all training sets, the training sets and the labels enter a judgment model DeCoVNet together, and training is carried out on the training sets; the masks of all the test sets and the test sets enter a judgment model DeCoVNet for testing; calculating local precision and uploading the local precision to a server;

3) The server collects the accuracy of the clients participating in training and calculates an accuracy average value;

4) And before the second epoch is operated, if the precision of a certain client is smaller than the precision average value, issuing m pieces of data to the client. The formula is as follows: m=i×n, where i= (acc) _avg -acc _i )/(acc _avg -acc _min ) N is the size of the shared data set, and the issued data set is not larger than the data volume of the client;

5) After the second epoch, the client with the issued shared data set trains the model together with the own data set until the whole model converges. .

The beneficial effects obtained by the invention by adopting the structure are as follows: according to the disease screening method based on federal learning, a model is built on a medical image through a deep learning convolutional neural network, so that the disease diagnosis accuracy is effectively improved; the node data of each hospital is comprehensively utilized by utilizing federal learning, and the generalization capability of the model is improved; a dynamic fusion strategy is provided, and the overall accuracy of the system is improved.

Drawings

FIG. 1 is a block diagram of a federal learning fusion method of the federal learning-based disease screening method of the present invention;

fig. 2 is a block diagram of a medical image deep learning method of the disease screening method based on federal learning.

The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention; all other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

As shown in fig. 1-2, the federal learning-based disease screening method of the present invention comprises the steps of:

1) The server builds a shared data set and transmits an initial model (U-Net++, deCoVNet) to the participating training clients;

2) When a client runs a first epoch, performing pre-training on a U-Net++ model by using an unsupervised learning training to obtain a mask with a mark and a training set with the mark; obtaining masks of all training sets by the U-Net++ model after the training sets are pre-trained; the mask of all training sets, the training sets and the labels enter a judgment model DeCoVNet together, and training is carried out on the training sets; the masks of all the test sets and the test sets enter a judgment model DeCoVNet for testing; calculating local precision and uploading the local precision to a server;

3) The server collects the accuracy of the clients participating in training and calculates an accuracy average value;

4) And before the second epoch is operated, if the precision of a certain client is smaller than the precision average value, issuing m pieces of data to the client. The formula is as follows: m=i×n, where i= (acc) _avg -acc _i )/(acc _avg -acc _min ) N is the size of the shared data set, and the issued data set is not larger than the data volume of the client;

5) After the second epoch, the client with the issued shared data set trains the model together with the own data set until the whole model converges.

When the method is specifically used, a user firstly sets a shared data set, then in the first epoch, after n iterations are carried out on the client, the precision is uploaded to a server, and the server collects all the precision of the client participating in training and calculates a mean value. If the precision of the ith client is lower than the precision average value, the data volume of the issued shared data (the data volume is not greater than the data volume of the client itself) is calculated, and if the precision of the ith client is higher than the precision average value, the shared data value is not issued. Finally, clients with shared datasets in the remaining epochs are trained until the model converges. Aiming at the characteristic that the dense population cities lead to the fact that the daily diagnosis of medical images is more, doctors can face the situation that the judging speed of a plurality of medical images is low, and therefore an artificial intelligent model is needed to help the doctors to judge diseases. The U-Net++ model is utilized to divide the medical image (judge the disease area), then the judgment model (DeCoVNet) is utilized to judge whether the disease exists in the divided part, and the above is the whole working flow of the invention, and the step is repeated when the method is used next time.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.

Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

The invention and its embodiments have been described above with no limitation, and the actual construction is not limited to the embodiments of the invention as shown in the drawings. In summary, if one of ordinary skill in the art is informed by this disclosure, a structural manner and an embodiment similar to the technical solution should not be creatively devised without departing from the gist of the present invention.

Claims (1)

1. A disease screening method based on federal learning, characterized in that; the method comprises the following steps:

1) The server builds a shared data set and transmits the initial model to the training client;

2) When a client runs a first epoch, performing pre-training on a U-Net++ model by using an unsupervised learning training to obtain a mask with a mark and a training set with the mark; obtaining masks of all training sets by the U-Net++ model after the training sets are pre-trained; the mask of all training sets, the training sets and the labels enter a judgment model DeCoVNet together, and training is carried out on the training sets; the masks of all the test sets and the test sets enter a judgment model DeCoVNet for testing; calculating local precision and uploading the local precision to a server;

3) The server collects the accuracy of the clients participating in training and calculates an accuracy average value;

4) Before the second epoch is operated, if the precision of a certain client is smaller than the precision average value, m pieces of data are issued to the client, and the formula is as follows: m=i×n, where i= (acc) _avg -acc _i )/(acc _avg -acc _min ) N is the size of the shared data set, and the issued data set is not larger than the data volume of the client;

5) After the second epoch, the client with the issued shared data set trains the model together with the own data set until the whole model converges.