Method for improving the accuracy of fluorescence molecular tomography based on multi-wavelength concurrent reconstruction

• DOI: 10.1063/5.0056883
• Publication Date: 2022-04-07T14:19:57Z
• Authors: Huiquan Wang; Tianzi Feng; Xinming Dong; Zhe Zhao; Guang Han; Jinhai Wang; Wenjuan Ma; Rong Wang; Minghu Liu; Jinghong Miao
• Keywords: Feature (linguistics); Reconstruction algorithm; Diffuse optical imaging

A Concurrent-wavelength Reconstruction Algorithm (CRA) based on multi-wavelength information fusion is proposed in this paper that aims to further improve the accuracy of Fluorescence Molecular Tomography (FMT) reconstruction. Combining multi-spectral data with FMT technology, 650 and 750 nm wavelengths near-infrared was used increase feature dominant 850 wavelength effectively. Principal component analysis, which can remove redundant achieve dimensionality reduction, then utilized extract information. Finally, tomographic reconstruction anomalies performed stacked auto-encoder neural network model. The comparison results numerical experiments showed effect CRA superior performance single correlation coefficient between reconstructed anomalies' fluorescence yield values real remained at 0.95 or more under noise different levels signal-to-noise ratios. Therefore, could effectively ill-posedness inverse problem, enhance