Single-energy CT energy spectrum imaging method based on deep learning

Abstract

The invention discloses a single-energy CT energy spectrum imaging method based on deep learning, and the method comprises the following steps: taking a single-energy CT image and a label high-energyCT image as a training sample, and forming a training set; constructing an image conversion model for predicting and outputting a high-energy CT image according to the input single-energy CT image based on a deep learning network, and training the image conversion model by utilizing the training set to determine model parameters of the image conversion model; and inputting a single-energy CT imageto be imaged into the image conversion model determined by the model parameters, and calculating and outputting a high-energy CT image. The method can achieve the quick, accurate and robust obtainingof the high-energy CT image through the single-energy CT image, and meets the clinical demands.

Description

technical field [0001] The invention relates to the technical field of medical engineering, in particular to a single-energy CT spectral imaging method based on deep learning. Background technique [0002] At present, modern X-ray CT imaging is widely used in medical clinical diagnosis and treatment, which has great social value and significance. In recent years, with the continuous emergence of various new CT imaging modalities, spectral CT and its material decomposition properties have shown great clinical potential. At present, spectral CT imaging technology is widely used in clinical diagnosis such as contouring of diseased organs, virtual single-energy imaging, virtual non-enhanced imaging, quantification of liver fibrosis, diagnosis of gout, and arterial CT angiography. [0003] The current spectral CT imaging technologies mainly include multiple scanning, fast kVp switching technology, double-layer detector technology, photon counting detector technology and dual-sou...

AI Technical Summary

Problems solved by technology

This scheme can flexibly adjust the tube voltage to obtain high-quality CT images, but it is limited by the cross-scattering of photons generated by the two tubes. In addition, neither X-ray tube imaging scheme can obtain accurate and consistent dual-energy projections.

The disadvantages of these spectral CT imaging technologies are that the hardware implementation is difficult, the reconstruction algorithm is relatively complex, and the radiation dose to the patient is increased.

Images