Active incremental training method for deep learning multi-class medical image classification

Abstract

The invention discloses an active incremental training method for deep learning multi-class medical image classification. The method comprises the following steps: 1, performing preliminary data cleaning and preprocessing on a medical image data set; 2, randomly selecting initial data, and carrying out initial training on the network model; 3, testing the rest samples in the data set to obtain thecorrespondence between the prediction score and the lesion category; 4, performing cross expansion on residual samples in the data set, and actively screening candidate samples; 5, performing furtherdata set cleaning; 6, performing incremental training on the model; and 7, testing the model after incremental training, if the accuracy is stable, ending the training, and otherwise, repeating the steps 4 to 7. According to the method, an AIFT method is improved, and the problems of difficult medical image classification, low training efficiency and the like caused by data imbalance are solved.The problem that the application effect of deep learning in the field of lesion classification is poor is solved, and the auxiliary effect on disease diagnosis of doctors is improved.

Description

technical field

[0001] The invention relates to a training method for medical image classification, in particular to an active incremental training method for deep learning multi-category medical image classification. Background technique

[0002] With the emergence of new medical imaging technology and equipment and the development of computer technology, the role and influence of medical image processing technology on medical research and clinical practice is increasing. Medical image processing technology has been highly valued by scholars at home and abroad. In recent years, with the rise of deep learning (Deep learning, also called Feature learning) methods, feature learning has received the focus of machine learning research. Deep learning uses deep neural networks to automatically learn effective feature representations in a data-driven form, and quickly subverts the research framework based on artificial features in many machine learning related application fields, b...

Images