Medical image classification method and device, medium and electronic equipment

Abstract

The invention relates to the field of machine learning, and discloses a medical image classification method and device, a medium and electronic equipment. The method comprises the following steps: selecting a target medical image sample from an unlabeled medical image sample set by utilizing an active learning framework, wherein a query strategy of the active learning framework is provided by a reinforcement learning model; inputting the target medical image sample labeled by the labeling expert into a medical image classification model, and training the medical image classification model; ifthe training does not meet the preset condition, obtaining a training result, training a reinforcement learning model based on the training result, updating a query strategy by utilizing the trained reinforcement learning model, and turning to a sample selection step until the training meets the preset condition; and inputting to-be-classified medical image data into the trained medical image classification model for classification. According to the method, a long-acting working mechanism for training the medical image classification model through man-machine cooperation is established, the labeling cost is reduced, and the labeling efficiency is improved.

Description

technical field [0001] The present disclosure relates to the technical field of machine learning, and in particular to a medical image classification method, device, medium and electronic equipment. Background technique [0002] With the development of software and hardware platforms and medical imaging technology, various medical imaging data covering different parts of the human body are acquired and stored in large quantities. Medical imaging data can well assist medical diagnosis. In the face of a large amount of medical imaging data, it is particularly important to use artificial intelligence to assist medical diagnosis and analysis. Medical imaging disease classification is a key issue in medical imaging diagnosis and data analysis. From the perspective of medical applications, its purpose is to classify original images according to image features and provide a basis for clinical diagnosis. However, the machine learning model used in classification needs to label med...

AI Technical Summary

Problems solved by technology

[0004] However, if active learning is to be used for sample selection, for different data modalities or scenarios, it is often necessary to design in advance based on expert experience and combine a large number of trial and error experiments to design query strategies in active learning. Experienced experts carry out fine algorithm design, and at the same time need to spend a lot of computing resources for long-term training to test out algorithm parameter configurations for different data modalities. Therefore, when using active learning to train medical image classification models, There are problems such as high labeling cost, low labeling efficiency and poor adaptability of query strategies in different scenarios

Images