Dual-energy CT image decomposition method based on CNN (convolutional neural network)

Abstract

The invention relates to the technical fields of medical dual-energy image decomposition and image processing, in particular to a dual-energy CT image decomposition method and particularly provides adual-energy CT image decomposition method based on a CNN (convolutional neural network). The dual-energy CT image decomposition method based on the CNN comprises the following steps: designing a CNN model to serve as a mapping function D (mu H, L; theta) of a dual-energy decomposition model; training the CNN with the CNN model and a training data set, and effectively estimating the CNN parameter theta; efficiently decomposing substrate materials of dual-energy CT images with the trained CNN and the CNN parameter theta obtained in step 2. Through establishment of the dual-input dual-output CNNmodel and cross convolution, reasonable shunt of different substrate materials of high-energy CT images and low-energy CT images is realized, so that quality of decomposition of the substrate materials of the dual-energy CT images is improved effectively.

Description

technical field [0001] The present invention relates to the technical field of medical dual-energy image decomposition and image processing, in particular to a dual-energy CT image decomposition method, in particular to a convolutional neural network-based dual-energy CT image decomposition method. Background technique [0002] Dual-energy CT image reconstruction has been increasingly used in medical imaging, safety inspection, nondestructive testing and other fields. Compared with traditional single-energy spectral CT imaging technology, dual-energy CT can use image attenuation information under different energy spectra to realize Identification of different substance materials. Dual-energy CT technology has broken the physical limitations of traditional single-energy spectrum CT, and has become a hot and difficult issue in the field of CT imaging. [0003] The core theory of dual-energy CT imaging technology is the dual-energy CT image reconstruction algorithm, in which t...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem that the base material image obtained by the existing dual-energy CT image decomposition method contains a large amount of noise and the signal-to-noise ratio is low, the present invention provides a dual-energy CT image decomposition method based on convolutional neural network, through dual input, dual The establishment of the output convolutional neural network model and cross-convolution realizes the reasonable shunting of different base materials in high-energy CT images and low-energy CT images, thereby effectively improving the quality of base material decomposition in dual-energy CT images

Images