Hybrid reconstruction method for multispectral bioluminescence tomography with log-sum regularization

Fluorescence molecular tomography based on an online maximum a posteriori estimation algorithm

Fluorescence molecular tomography (FMT) is a non-invasive, radiation-free, and highly sensitive optical molecular imaging technique for early tumor detection. However, inadequate measurement information along with significant scattering of near-infrared light within the tissue leads to high ill-posedness in the inverse problem of FMT. To improve the quality and efficiency of FMT reconstruction, we build a reconstruction model based on log-sum regularization and introduce an online maximum a posteriori estimation (OPE) algorithm to solve the non-convex optimization problem. The OPE algorithm approximates a stationary point by evaluating the gradient of the objective function at each iteration, and its notable strength lies in the remarkable speed of convergence. The results of simulations and experiments demonstrate that the OPE algorithm ensures good reconstruction quality and exhibits outstanding performance in terms of reconstruction efficiency.

A Graph-guided Hybrid Regularization Method For Bioluminescence Tomography

BACKGROUND AND OBJECTIVE

Bioluminescence tomography (BLT) is a powerful and sensitive imaging technique having great potential in preclinical application, such as tumor imaging, monitoring and therapy, etc. Regularization plays an important role in BLT reconstruction for considering the priori information to overcome the inherent ill-posedness of the inverse problem. Therefore, well-designed regularization term and sophisticated algorithm for solving the consequent optimization problem are key to improve the BLT quality.

METHODS

To balance the sparsity, smoothness and morphological characteristics of the bioluminescence targets, we constructed a novel Graph-Guided Hybrid Regularization (GGHR) method by combining graph-guided penalty term with L₁ and L₂ norm regularizer. To solve the corresponding minimization problem with hybrid penalties, the dual decomposition and Nesterov's smoothing technique were adopted to decouple and transform the non-separable and non-smooth graph-guided penalty term into a differential smooth approximation form, which was solved by the fast iterative shrinkage thresholding algorithm.

RESULTS

The performance of the proposed GGHR method was verified and evaluated through a series of simulation, phantom and in vivo experiments. The comparison results demonstrated that the GGHR method outperformed current mainstream reconstruction algorithms in spatial localization, morphology recovery and in vivo practicality.

CONCLUSIONS

The proposed GGHR method is a robust and practicality reconstruction algorithm for further highlighting the positive effect of hybrid regularization on BLT applications.

Bioluminescence Tomography Based on One-Dimensional Convolutional Neural Networks

Bioluminescent tomography (BLT) has increasingly important applications in preclinical studies. However, the simplified photon propagation model and the inherent ill-posedness of the inverse problem limit the quality of BLT reconstruction. In order to improve the reconstruction accuracy of positioning and reconstruction efficiency, this paper presents a deep-learning optical reconstruction method based on one-dimensional convolutional neural networks (1DCNN). The nonlinear mapping relationship between the surface photon flux density and the distribution of the internal bioluminescence sources is directly established, which fundamentally avoids solving the ill-posed inverse problem iteratively. Compared with the previous reconstruction method based on multilayer perceptron, the training parameters in the 1DCNN are greatly reduced and the learning efficiency of the model is improved. Simulations verify the superiority and stability of the 1DCNN method, and the in vivo experimental results further show the potential of the proposed method in practical applications.