Bioluminescence tomography reconstruction algorithm based on multitask Bayes compressed sensing method

Abstract

The invention discloses a bioluminescence tomography reconstruction algorithm based on a multitask Bayes compressed sensing method and belongs to the field of medical image processing. The bioluminescence tomography reconstruction algorithm based on the multitask Bayes compressed sensing method comprises the steps that firstly, the intrinsic relevance between multiple spectra is explored according to the rule of transmission of model light of a high-order approximation model in biological tissue and based on the multitask learning method, the intrinsic relevance between the multiple spectra is taken as prior information to be infused in the reconstruction algorithm so as to reduce the morbidity of BLT reconstruction, and finally, three-dimensional reconstruction of a fluorescent light source is achieved on the basis. Compared with other bioluminescence tomography reconstruction algorithms, the bioluminescence tomography reconstruction algorithm based on the multitask Bayes compressed sensing method has the advantages that the intrinsic relevance between the multiple spectra is further fused, the morbidity of BLT reconstruction is reduced, accurate reconstruction and positioning of the fluorescent light source are achieved, and the calculation efficiency can be greatly improved.

Description

technical field [0001] The invention belongs to the field of medical image processing, and relates to a bioluminescence tomography reconstruction algorithm based on a multi-task Bayesian compressed sensing method. Background technique [0002] Optical molecular imaging is a rapidly developing molecular imaging technology, which combines optical processes with certain molecular properties to analyze and process biofluorescence or excitation fluorescence in the target body, and conduct qualitative and quantitative studies. [0003] The most representative imaging methods in optical molecular imaging technology are fluorescence imaging (Fluorescence Imaging) and Bioluminescence Imaging (BLI). They are all two-dimensional bioluminescence imaging technologies. Although this imaging technology is convenient and simple to apply, there are limitations in the application process of this two-dimensional imaging method, especially for the limitation of imaging depth, the two-dimensiona...

AI Technical Summary

Problems solved by technology

[0006] Most of the existing methods to reduce its morbidity are based on the multispectral information and the sparse characteristics of the light source to carry out the research of BLT reconstruction methods, but these methods do not consider the correlation between multispectrum

Images