Convolutional neural network medical CT image denoising method

Abstract

The invention belongs to the technical field of medical image denoising, and particularly relates to a convolutional neural network medical CT image denoising method, which comprises the following steps: firstly, performing data acquisition, and then establishing a basic model according to the acquired data; meanwhile, connecting a basic network layer, a middle network layer and an upper network layer through neurons and nodes, forming a convolutional neural network by the basic network layer, the middle network layer and the upper network layer, and enabling the convolutional neural network to perform translation invariant classification on input information according to a hierarchical structure of the convolutional neural network. According to the invention, neuron can conveniently perform two-dimensional data acquisition when acquiring the feature data, so that the acquisition direction is prevented from being too single when acquiring the feature data, meanwhile, the convolutionalneural network has a representation learning capability, multiple groups of data can be integrated so as to prevent edge data of a CT image from being lost, and thus the CT imaging area range is improved.

Description

technical field [0001] The invention relates to the technical field of medical image denoising, in particular to a convolutional neural network medical CT image denoising method. Background technique [0002] Convolutional neural network is a kind of feed-forward neural network with convolution calculation and deep structure, and it is one of the representative algorithms of deep learning. The convolutional neural network has the ability to learn representations and can classify the input information according to its hierarchical structure. Therefore, it is also called a "translational invariant artificial neural network." Research on convolutional neural networks began in the 1980s to In the 1990s, after the 21st century, with the introduction of deep learning theory and the improvement of numerical computing equipment, convolutional neural networks have developed rapidly and have been applied in computer vision, natural language processing and other fields. [0003] CT im...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a convolutional neural network medical CT image denoising method to solve the problem of single directionality and limited filtering area of ​​the traditional denoising method proposed in the above-mentioned background technology

Images