Bayesian Framework Based Direct Reconstruction of Fluorescence Parametric Images

Robust reconstruction of fluorescence molecular tomography based on adaptive adversarial learning strategy

Objective.Fluorescence molecular tomography (FMT) is a promising molecular imaging modality for quantifying the three-dimensional (3D) distribution of tumor probes in small animals. However, traditional deep learning reconstruction methods that aim to minimize the mean squared error (MSE) and iterative regularization algorithms that rely on optimal parameters are typically influenced by strong noise, resulting in poor FMT reconstruction robustness.Approach.In this letter, we propose an adaptive adversarial learning strategy (3D-UR-WGAN) to achieve robust FMT reconstructions. Unlike the pixel-based MSE criterion in traditional CNNs or the regularization strategy in iterative solving schemes, the reconstruction strategy can greatly facilitate the performance of the network models through alternating loop training of the generator and the discriminator. Second, the reconstruction strategy combines the adversarial loss in GANs with the L1 loss to significantly enhance the robustness and preserve image details and textual information.Main results.Both numerical simulations and physical phantom experiments demonstrate that the 3D-UR-WGAN method can adaptively eliminate the effects of different noise levels on the reconstruction results, resulting in robust reconstructed images with reduced artifacts and enhanced image contrast. Compared with the state-of-the-art methods, the proposed method achieves better reconstruction performance in terms of target shape recovery and localization accuracy.Significance.This adaptive adversarial learning reconstruction strategy can provide a possible paradigm for robust reconstruction in complex environments, and also has great potential to provide an alternative solution for solving the problem of poor robustness encountered in other optical imaging modalities such as diffuse optical tomography, bioluminescence imaging, and Cherenkov luminescence imaging.

Indirect and direct estimation of pharmacokinetic parameters in dynamic diffuse fluorescence tomography by adaptive extended Kalman filtering

Pharmacokinetic parameter estimation with the support of dynamic diffuse fluorescence tomography (DFT) can provide helpful diagnostic information for tumor differentiation and monitoring. Adaptive extended Kalman filtering (AEKF) as a nonlinear filter method has the merits of high quantitativeness, noise robustness, and initialization independence. In this paper, indirect and direct AEKF schemes combining with a commonly used two-compartment model were studied to estimate the pharmacokinetic parameters based on our self-designed dynamic DFT system. To comprehensively compare the performances of both schemes, the selection of optimal noise covariance matrices affecting estimation results was first studied, then a series of numerical simulations with the metabolic time ranged from 4.16 min to 38 min was carried out and quantitatively evaluated. The comparison results show that the direct AEKF outperforms the indirect EKF in estimation accuracy at different metabolic velocity and demonstrates stronger stability at the large metabolic velocity. Furtherly, the in vivo experiment was conducted to achieve the indocyanine green pharmacokinetic-rate images in the mouse liver. The experimental results confirmed the capability of both schemes to estimate the pharmacokinetic-rate images and were in agreement with the theory predictions and the numerical simulation results.

In vivo accurate detection of the liver tumor with pharmacokinetic parametric images from dynamic fluorescence molecular tomography

SIGNIFICANCE

Pharmacokinetic parametric images in dynamic fluorescence molecular tomography (FMT) can describe three-dimensional (3D) physiological and pathological information inside biological tissues, potentially providing quantitative assessment tools for biological research and drug development.

AIM

In vivo imaging of the liver tumor with pharmacokinetic parametric images from dynamic FMT based on the differences in metabolic properties of indocyanine green (ICG) between normal liver cells and tumor liver cells inside biological tissues.

APPROACH

First, an orthotopic liver tumor mouse model was constructed. Then, with the help of the FMT/computer tomography (CT) dual-modality imaging system and the direct reconstruction algorithm, 3D imaging of liver metabolic parameters in nude mice was achieved to distinguish liver tumors from normal tissues. Finally, pharmacokinetic parametric imaging results were validated against in vitro anatomical results.

RESULTS

This letter demonstrates the ability of dynamic FMT to monitor the pharmacokinetic delivery of the fluorescent dye ICG in vivo, thus, enabling the distinction between normal and tumor tissues based on the pharmacokinetic parametric images derived from dynamic FMT.

CONCLUSIONS

Compared with CT structural imaging technology, dynamic FMT combined with compartmental modeling as an analytical method can obtain quantitative images of pharmacokinetic parameters, thus providing a more powerful research tool for organ function assessment, disease diagnosis and new drug development.

A review of advances in imaging methodology in fluorescence molecular tomography

Objective. Fluorescence molecular tomography (FMT) is a promising non-invasive optical molecular imaging technology with strong specificity and sensitivity that has great potential for preclinical and clinical studies in tumor diagnosis, drug development and therapeutic evaluation. However, the strong scattering of photons and insufficient surface measurements make it very challenging to improve the quality of FMT image reconstruction and its practical application for early tumor detection. Therefore, continuous efforts have been made to explore more effective approaches or solutions in the pursuit of high-quality FMT reconstructions. Approach. This review takes a comprehensive overview of advances in imaging methodology for FMT, mainly focusing on two critical issues in FMT reconstructions: improving the accuracy of solving the forward physical model and mitigating the ill-posed nature of the inverse problem from a methodological point of view. More importantly, numerous impressive and practical strategies and methods for improving the quality of FMT reconstruction are summarized. Notably, deep learning methods are discussed in detail to illustrate their advantages in promoting the imaging performance of FMT thanks to large datasets, the emergence of optimized algorithms and the application of innovative networks. Main results. The results demonstrate that the imaging quality of FMT can be effectively promoted by improving the accuracy of optical parameter modeling, combined with prior knowledge, and reducing dimensionality. In addition, the traditional regularization-based methods and deep neural network-based methods, especially end-to-end deep networks, can enormously alleviate the ill-posedness of the inverse problem and improve the quality of FMT image reconstruction. Significance. This review aims to illustrate a variety of effective and practical methods for the reconstruction of FMT images that may benefit future research. Furthermore, it may provide some valuable research ideas and directions for FMT in the future, and could promote, to a certain extent, the development of FMT and other methods of optical tomography.

UHR-DeepFMT: Ultra-High Spatial Resolution Reconstruction of Fluorescence Molecular Tomography Based on 3-D Fusion Dual-Sampling Deep Neural Network

Fluorescence molecular tomography (FMT) is a promising and high sensitivity imaging modality that can reconstruct the three-dimensional (3D) distribution of interior fluorescent sources. However, the spatial resolution of FMT has encountered an insurmountable bottleneck and cannot be substantially improved, due to the simplified forward model and the severely ill-posed inverse problem. In this work, a 3D fusion dual-sampling convolutional neural network, namely UHR-DeepFMT, was proposed to achieve ultra-high spatial resolution reconstruction of FMT. Under this framework, the UHR-DeepFMT does not need to explicitly solve the FMT forward and inverse problems. Instead, it directly establishes an end-to-end mapping model to reconstruct the fluorescent sources, which can enormously eliminate the modeling errors. Besides, a novel fusion mechanism that integrates the dual-sampling strategy and the squeeze-and-excitation (SE) module is introduced into the skip connection of UHR-DeepFMT, which can significantly improve the spatial resolution by greatly alleviating the ill-posedness of the inverse problem. To evaluate the performance of UHR-DeepFMT network model, numerical simulations, physical phantom and in vivo experiments were conducted. The results demonstrated that the proposed UHR-DeepFMT can outperform the cutting-edge methods and achieve ultra-high spatial resolution reconstruction of FMT with the powerful ability to distinguish adjacent targets with a minimal edge-to-edge distance (EED) of 0.5 mm. It is assumed that this research is a significant improvement for FMT in terms of spatial resolution and overall imaging quality, which could promote the precise diagnosis and preclinical application of small animals in the future.

Optimization of data acquisition operation in optical tomography based on estimation theory

The data acquisition process is occasionally the most time consuming and costly operation in tomography. Currently, raster scanning is still the common practice in making sequential measurements in most tomography scanners. Raster scanning is known to be slow and such scanners usually cannot catch up with the speed of changes when imaging dynamically evolving objects. In this research, we studied the possibility of using estimation theory and our prior knowledge about the sample under test to reduce the number of measurements required to achieve a given image quality. This systematic approach for optimization of the data acquisition process also provides a vision toward improving the geometry of the scanner and reducing the effect of noise, including the common state-dependent noise of detectors. The theory is developed in the article and simulations are provided to better display discussed concepts.

An Artificial Intelligent Signal Amplification System for in vivo Detection of miRNA

MicroRNAs (miRNA) have been identified as oncogenic drivers and tumor suppressors in every major cancer type. In this work, we design an artificial intelligent signal amplification (AISA) system including double-stranded SQ (S, signal strand; Q, quencher strand) and FP (F, fuel strand; P, protect strand) according to thermodynamics principle for sensitive detection of miRNA in vitro and in vivo. In this AISA system for miRNA detection, strand S carries a quenched imaging marker inside the SQ. Target miRNA is constantly replaced by a reaction intermediate and circulatively participates in the reaction, similar to enzyme. Therefore, abundant fluorescent substances from S and SP are dissociated from excessive SQ for in vitro and in vivo visualization. The versatility and feasibility for disease diagnosis using this system were demonstrated by constructing two types of AISA system to detect Hsa-miR-484 and Hsa-miR-100, respectively. The minimum target concentration detected by the system in vitro (10 min after mixing) was 1/10th that of the control group. The precancerous lesions of liver cancer were diagnosed, and the detection accuracy were larger than 94% both in terms of location and concentration. The ability to establish this design framework for AISA system with high specificity provides a new way to monitor tumor progression and to assess therapeutic responses.

3D deep encoder-decoder network for fluorescence molecular tomography

Fluorescence molecular tomography (FMT) is a promising and noninvasive in vivo functional imaging modality. However, the quality of FMT reconstruction is limited by the simplified linear model of photon propagation. Here, an end-to-end three-dimensional deep encoder-decoder (3D-En-Decoder) network is proposed to improve the quality of FMT reconstruction. It directly establishes the nonlinear mapping relationship between the inside fluorescent source distribution and the boundary fluorescent signal distribution. Thus the reconstruction inaccuracy caused by the simplified linear model can be fundamentally avoided by the proposed network. Both numerical simulations and phantom experiments were carried out, and the results demonstrated that the 3D-En-Decoder network can greatly improve image quality and significantly reduce reconstruction time compared with conventional methods.

Parameterized level-set based pharmacokinetic fluorescence optical tomography using the regularized Gauss-Newton filter

Pharmacokinetic tomography is emerging as an important methodology for detecting abnormalities in tissue based upon spatially varying estimation of the pharmacokinetic rates governing the leakage of an injected fluorophore between blood plasma and tissue. We present a shape-based reconstruction framework of a compartment-model based formulation of this dynamic fluorescent optical tomography problem to solve for the pharmacokinetic rates and concentrations of the fluorophore from time-varying log intensity measurements of the optical signal. The compartment-model based state variable model is set up in a radial basis function parameterized level set setting. The state (concentrations) and (pharmacokinetic) parameter estimation problem is solved with an iteratively regularized Gauss-Newton filter in a trust-region framework. Reconstructions obtained using this scheme for noisy data obtained from cancer mimicking numerical phantoms of near/sub-cm sizes show a good localization of the affected regions and reasonable estimates of the pharmacokinetic rates and concentration curves.

Recent methodology advances in fluorescence molecular tomography

Molecular imaging (MI) is a novel imaging discipline that has been continuously developed in recent years. It combines biochemistry, multimodal imaging, biomathematics, bioinformatics, cell & molecular physiology, biophysics, and pharmacology, and it provides a new technology platform for the early diagnosis and quantitative analysis of diseases, treatment monitoring and evaluation, and the development of comprehensive physiology. Fluorescence Molecular Tomography (FMT) is a type of optical imaging modality in MI that captures the three-dimensional distribution of fluorescence within a biological tissue generated by a specific molecule of fluorescent material within a biological tissue. Compared with other optical molecular imaging methods, FMT has the characteristics of high sensitivity, low cost, and safety and reliability. It has become the research frontier and research hotspot of optical molecular imaging technology. This paper took an overview of the recent methodology advances in FMT, mainly focused on the photon propagation model of FMT based on the radiative transfer equation (RTE), and the reconstruction problem solution consist of forward problem and inverse problem. We introduce the detailed technologies utilized in reconstruction of FMT. Finally, the challenges in FMT were discussed. This survey aims at summarizing current research hotspots in methodology of FMT, from which future research may benefit.

Bioluminescence Tomography Based on Gaussian Weighted Laplace Prior Regularization for In Vivo Morphological Imaging of Glioma

Bioluminescence tomography (BLT) is a powerful non-invasive molecular imaging tool for in vivo studies of glioma in mice. However, because of the light scattering and resulted ill-posed problems, it is challenging to develop a sufficient reconstruction method, which can accurately locate the tumor and define the tumor morphology in three-dimension. In this paper, we proposed a novel Gaussian weighted Laplace prior (GWLP) regularization method. It considered the variance of the bioluminescence energy between any two voxels inside an organ had a non-linear inverse relationship with their Gaussian distance to solve the over-smoothed tumor morphology in BLT reconstruction. We compared the GWLP with conventional Tikhonov and Laplace regularization methods through various numerical simulations and in vivo orthotopic glioma mouse model experiments. The in vivo magnetic resonance imaging and ex vivo green fluorescent protein images and hematoxylin-eosin stained images of whole head cryoslicing specimens were utilized as gold standards. The results demonstrated that GWLP achieved the highest accuracy in tumor localization and tumor morphology preservation. To the best of our knowledge, this is the first study that achieved such accurate BLT morphological reconstruction of orthotopic glioma without using any segmented tumor structure from any other structural imaging modalities as the prior for reconstruction guidance. This enabled BLT more suitable and practical for in vivo imaging of orthotopic glioma mouse models.

Compactly Supported Radial Basis Function-Based Meshless Method for Photon Propagation Model of Fluorescence Molecular Tomography

Fluorescence Molecular Tomography (FMT) is a powerful imaging modality for the research of cancer diagnosis, disease treatment and drug discovery. Via three-dimensional (3-D) imaging reconstruction, it can quantitatively and noninvasively obtain the distribution of fluorescent probes in biological tissues. Currently, photon propagation of FMT is conventionally described by the Finite Element Method (FEM), and it can obtain acceptable image quality. However, there are still some inherent inadequacies in FEM, such as time consuming, discretization error and inflexibility in mesh generation, which partly limit its imaging accuracy. To further improve the solving accuracy of photon propagation model (PPM), we propose a novel compactly supported radial basis functions (CSRBFs)-based meshless method (MM) to implement the PPM of FMT. We introduced a series of independent nodes and continuous CSRBFs to interpolate the PPM, which can avoid complicated mesh generation. To analyze the performance of the proposed MM, we carried out numerical heterogeneous mouse simulation to validate the simulated surface fluorescent measurement. Then we performed an in vivo experiment to observe the tomographic reconstruction. The experimental results confirmed that our proposed MM could obtain more similar surface fluorescence measurement with the golden standard (Monte-Carlo method), and more accurate reconstruction result was achieved via MM in in vivo application.

Cone Beam X-ray Luminescence Computed Tomography Based on Bayesian Method

X-ray luminescence computed tomography (XLCT), which aims to achieve molecular and functional imaging by X-rays, has recently been proposed as a new imaging modality. Combining the principles of X-ray excitation of luminescence-based probes and optical signal detection, XLCT naturally fuses functional and anatomical images and provides complementary information for a wide range of applications in biomedical research. In order to improve the data acquisition efficiency of previously developed narrow-beam XLCT, a cone beam XLCT (CB-XLCT) mode is adopted here to take advantage of the useful geometric features of cone beam excitation. Practically, a major hurdle in using cone beam X-ray for XLCT is that the inverse problem here is seriously ill-conditioned, hindering us to achieve good image quality. In this paper, we propose a novel Bayesian method to tackle the bottleneck in CB-XLCT reconstruction. The method utilizes a local regularization strategy based on Gaussian Markov random field to mitigate the ill-conditioness of CB-XLCT. An alternating optimization scheme is then used to automatically calculate all the unknown hyperparameters while an iterative coordinate descent algorithm is adopted to reconstruct the image with a voxel-based closed-form solution. Results of numerical simulations and mouse experiments show that the self-adaptive Bayesian method significantly improves the CB-XLCT image quality as compared with conventional methods.

Direct reconstruction in CT-analogous pharmacokinetic diffuse fluorescence tomography: two-dimensional simulative and experimental validations

We present a generalized strategy for direct reconstruction in pharmacokinetic diffuse fluorescence tomography (DFT) with CT-analogous scanning mode, which can accomplish one-step reconstruction of the indocyanine-green pharmacokinetic-rate images within in vivo small animals by incorporating the compartmental kinetic model into an adaptive extended Kalman filtering scheme and using an instantaneous sampling dataset. This scheme, compared with the established indirect and direct methods, eliminates the interim error of the DFT inversion and relaxes the expensive requirement of the instrument for obtaining highly time-resolved date-sets of complete 360 deg projections. The scheme is validated by two-dimensional simulations for the two-compartment model and pilot phantom experiments for the one-compartment model, suggesting that the proposed method can estimate the compartmental concentrations and the pharmacokinetic-rates simultaneously with a fair quantitative and localization accuracy, and is well suitable for cost-effective and dense-sampling instrumentation based on the highly-sensitive photon counting technique.