Medical image focus detection modeling method, device and system based on federated learning

Abstract

The invention discloses a medical image focus detection modeling method, device and system based on federated learning, and the method comprises the steps: enabling a global server S to transmit a generated global parameter [omega]<0> to local focus recognition clients C<k>; generating a global parameter [omega]<theta+1> by using detection head network parameters returned by the K local focus identification clients C<k>; and sending the global parameter [omega]<theta+1> to each local focus identification client C<k> to obtain a corresponding medical image focus detection model. The training information of the intermediate model is transmitted to a data holder through codes, respective data information does not need to be shared, and the model is integrated through a corresponding strategy, so that better training and prediction results are returned.

Description

technical field [0001] The invention belongs to the field of computer vision and deep learning, and in particular relates to a method, device and system for detecting and modeling medical imaging lesions based on federated learning. Background technique [0002] Nowadays, people's health awareness is increasing day by day, and they pay more and more attention to the acquisition of medical information. Medical imaging data has shown explosive growth, and smart medical care has also entered people's sight. Based on these image data, deep learning technology mines the underlying rules and information, creates accurate models, diagnoses and predicts diseases. In the early stage, the deep network trained by ImageNet was fine-tuned and applied to medical imaging tasks by using transfer learning, which accelerated the convergence speed of the model and improved the accuracy rate. However, medical datasets usually lack sufficient labeled data, and data augmentation to deal with lim...

AI Technical Summary

Problems solved by technology

Many medical institutions operate under strict privacy practices and may face legal, administrative or ethical constraints, which makes it usually not feasible to collect medical data centrally and share patient information with multiple parties, that is, there is a medical "data island" problem

However, centralized modeling obviously cannot achieve effective medical privacy protection. At the same time, the insufficient data volume of medical data and the large number of missing labels still affect the model accuracy.

Images