PET reconstruction method based on anatomical prior information

Abstract

A PET reconstruction method based on anatomical prior information relates to the medical PET imaging technology, and comprises the following steps: 1, obtaining a prior image; 2, extracting a functionF representing anatomical features in a high-dimensional space; 3, selecting a radial Gaussian kernel function; 4, adding a kernel method into the expectation maximization algorithm iterative reconstruction framework to represent the PET image in the reconstruction process; 5, finally obtaining a reconstruction result, adding the extracted priori information of the anatomical image with high spatial resolution into a kernel method reconstruction process based on machine learning, obtaining better PET image reconstruction quality, and improving an image signal-to-noise ratio and a quantitativeanalysis effect.

Description

technical field [0001] The invention relates to medical PET imaging technology, in particular to a PET reconstruction method based on anatomical prior information. Background technique [0002] Positron Emission Computed Tomography (PET), as a non-interventional tool for quantitatively studying functional activity in vivo, is being more and more widely used in clinical diagnosis, especially early diagnosis of diseases. The spatial resolution of PET is one of the core indicators of the PET system. Some physical characteristics of positrons and the limitations of the data acquisition mechanism lead to an inevitable reduction in spatial resolution, which is manifested as blurred images on the image, which restricts the PET system. In some applications that require high resolution, such as early tumor discovery, brain functional imaging, etc. [0003] The traditional PET image reconstruction method has high image noise, resulting in poor quantitative analysis and affecting imag...

AI Technical Summary

Problems solved by technology

The spatial resolution of PET is one of the core indicators of the PET system. Some physical characteristics of positrons and the limitations of the data acquisition mechanism lead to an inevitable reduction in spatial resolution, which is manifested as blurred images on the image, which restricts the PET system. In some applications that require high resolution, such as early tumor discovery, brain functional imaging, etc.

[0003] The traditional PET image reconstruction method has high image noise, resulting in poor quantitative analysis and affecting image diagnosis. In order to solve the above technical problems, a new technical solution is proposed.

Images