Optical tomography method and system based on K-nearest neighbor local connection network

Abstract

The invention belongs to the field of digital images, particularly relates to an optical tomography method and system based on a K-nearest neighbor local connection network, and aims to solve the problem that the reconstruction precision and imaging speed of existing FMT imaging cannot be considered at the same time. The method comprises the following steps: constructing a first sample by utilizing Monte Carlo simulation; utilizing the first sample to realize expansion of a training sample set in a sample combination mode; for the constructed K-nearest neighbor local connection network, training by using the training sample set, and optimizing a local connection sub-network by using residual learning; and performing internal light source reconstruction based on an appearance fluorescence image of the target object by using the trained K-nearest neighbor local connection network. According to the neural network method based on data driving, the reverse propagation process of photons ina living body is directly learned, and accurate and rapid excitation of fluorescence tomography is achieved.

Description

technical field [0001] The invention belongs to the field of digital images, and in particular relates to an optical tomographic imaging method and system based on a K-nearest neighbor local connection network. Background technique [0002] Fluorescence Molecular Imaging (FMI) is a two-dimensional optical molecular imaging technology, which can non-invasively detect the distribution of fluorescent probes in organisms. Compared with other medical imaging techniques, FMI has the advantages of high sensitivity, no radiation, and a wide variety of imaging probes. [0003] Fluorescence Molecular Tomography (FMT) is a three-dimensional fluorescence tomography technology that combines FMI and anatomical structure imaging (MRI / CT). This imaging technology first registers the surface spot information obtained by FMI to the three-dimensional anatomical structure image, and then reversely reconstructs the three-dimensional distribution information of the fluorescent light source insid...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem that the reconstruction accuracy and imaging speed of the existing FMT imaging cannot be balanced, the first aspect of the present invention proposes an optical tomography method based on the K-nearest neighbor local connection network , the imaging method comprises the following steps:

Images