Medical image classification method combining wavelet transform and tensor network

Abstract

The invention relates to the technical field of medical image classification, and particularly discloses a medical image classification method combining wavelet transform and a tensor network. A coarse graining network is provided, the coarse graining network combines wavelet transform and MERA, that is, D4 wavelets are coded into the MERA to form a Wavelet MERA model with fixed internal parameters; and a tensor classification network like a full connection layer is also constructed. According to the invention, the MNIST data set, the Covid-19 data set and the LIDC data set are used for multi-dimensional verification, and the result shows that the accuracy stability of the wavelet MERA is high, and the wavelet MERA has better coarse graining ability than a CNNs deep neural network, so that the wavelet MERA can reduce the parameter quantity of the model to a greater extent while the precision is ensured. The result shows that the Wavelet MERA is superior to the current mainstream deep neural network in classification and is also superior to the common wavelet transform in the aspect of data preprocessing. In addition, the wavelet MERA also has the advantage of interpretability of the tensor network itself.

Description

technical field [0001] The invention relates to the technical field of medical image classification, in particular to a medical image classification method combining wavelet transform and tensor network. Background technique [0002] In recent decades, machine learning has developed vigorously, and many algorithms have emerged, which have been proved to be good enough in their respective times, such as Naive Bayes ( Bayes), kernel methods, decision trees, random forests, and Neural Networks (NNs). In recent years, deep neural networks have achieved amazing success. Convolutional Neural Networks (CNNs) is one of the most successful deep neural networks. Its convolutional layer can extract important features from the original data, and then the data is compressed by the pooling layer, and finally input into the fully connected layer. Get the prediction result. [0003] In the field of medical image analysis, CNNs models and their variants are widely used in colonoscopy, H...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a medical image classification method combined with wavelet transform and tensor network, and the technical problem to be solved is that the existing medical image classification method cannot take into account high accuracy, avoid overfitting and interpretability in a small data set

Images