Bioluminescence Tomography Based on One-Dimensional Convolutional Neural Networks

Bioluminescence as a functional tool for visualizing and controlling neuronal activity in vivo

The use of bioluminescence as a reporter for physiology in neuroscience is as old as the discovery of the calcium-dependent photon emission of aequorin. Over the years, luciferases have been largely replaced by fluorescent reporters, but recently, the field has seen a renaissance of bioluminescent probes, catalyzed by unique developments in imaging technology, bioengineering, and biochemistry to produce luciferases with previously unseen colors and intensity. This is not surprising as the advantages of bioluminescence make luciferases very attractive for noninvasive, longitudinal in vivo observations without the need of an excitation light source. Here, we review how the development of dedicated and specific sensor-luciferases afforded, among others, transcranial imaging of calcium and neurotransmitters, or cellular metabolites and physical quantities such as forces and membrane voltage. Further, the increased versatility and light output of luciferases have paved the way for a new field of functional bioluminescence optogenetics, in which the photon emission of the luciferase is coupled to the gating of a photosensor, e.g., a channelrhodopsin and we review how they have been successfully used to engineer synthetic neuronal connections. Finally, we provide a primer to consider important factors in setting up functional bioluminescence experiments, with a particular focus on the genetic model Caenorhabditis elegans, and discuss the leading challenges that the field needs to overcome to regain a competitive advantage over fluorescence modalities. Together, our paper caters to experienced users of bioluminescence as well as novices who would like to experience the advantages of luciferases in their own hand.

Development of an integrated dual-modality 3D bioluminescence tomography and ultrasound imaging system for small animal tumor imaging

Ultrasound (US) is a valuable tool for imaging soft tissue and visualizing tumor contours. Taking the benefits of US, we presented an integrated dual-modality imaging system in this paper that achieves three-dimensional (3D) bioluminescence tomography (BLT) with multi-view bioluminescence images and 3D US imaging. The purpose of this system is to perform non-invasive, long-term monitoring of tumor growth in 3D images. US images can enhance the accuracy of the 3D BLT reconstruction and the bioluminescence dose within an object. Furthermore, an integrated co-registered scanning geometry was used to capture the fused BLT and US images. We validated the system with an in vivo experiment involving tumor-bearing mice. The results demonstrated the feasibility of reconstructing 3D BLT images in the tumor region using 3D US images. We used the dice coefficient and locational error to evaluate the similarity between the reconstructed source region and the actual source region. The dice coefficient was 88.5%, and the locational error was 0.4 mm when comparing the BLT and 3D US images. The hybrid BLT/US system could provide significant benefits for reconstructing the source of tumor location and conducting quantitative analysis of tumor size.

Structure-fused deep 3D hierarchical network: A bioluminescence tomography scheme for different imaging objects

Monte Carlo eXtreme (MCX) method has a unique advantage for deep neural network based bioluminescence tomography (BLT) reconstruction. However, this method ignores the distribution of sources energy and relies on the determined tissue structure. In this paper, a deep 3D hierarchical reconstruction network for BLT was proposed where the inputs were divided into two parts -- bioluminescence image (BLI) and anatomy of the imaged object by CT. Firstly, a parallel encoder is used to feature the original BLI & CT slices and integrate their features to distinguish the different tissue structure of imaging objects; Secondly, GRU is used to fit the spatial information of different slices and convert it into 3D features; Finally, the 3D features are decoded to the spacial and energy information of source by a symmetrical decoding structure. Our research suggested that this method can effectively compute the radiation intensity and the spatial distribution of the source for different imaging object.

K-CapsNet: K-Nearest Neighbor Based Convolution Capsule Network for Cerenkov Luminescence Tomography Reconstruction

Cerenkov luminescence tomography (CLT) has received significant attention as a promising imaging modality that can display the three-dimensional (3D) distribution of radioactive probes. However, the reconstruction of CLT suffers from severe ill-posed problem. It is difficult for traditional model-based method to obtain satisfactory result. Recently, deep learning-based method have shown great potential for accurate and efficient CLT reconstruction. In this study, a KNN-based convolution capsule network, named K-CapsNet, is proposed for cerenkov luminescence tomography. In K-CapsNet, the surface photon intensity is encoded in capsule form. The KNN-based convolution and K-means clustering are proposed for efficient encoding. Numerical simulation experiments have been carried out to verify the performance of K-CapsNet, and the results show that it performs superior in source localization and morphological restoration compared with existing methods.

Bioluminescence tomography reconstruction in conjunction with an organ probability map as an anatomical reference

To alleviate the ill-posedness of bioluminescence tomography (BLT) reconstruction, anatomical information from computed tomography (CT) or magnetic resonance imaging (MRI) is usually adopted to improve the reconstruction quality. With the anatomical information, different organs could be segmented and assigned with appropriate optical parameters, and the reconstruction could be confined into certain organs. However, image segmentation is a time-consuming and challenging work, especially for the low-contrast organs. In this paper, we present a BLT reconstruction method in conjunction with an organ probability map to effectively incorporate the anatomical information. Instead of using a segmentation with a fixed organ map, an organ probability map is established by registering the CT image of the mouse to the statistical mouse atlas with the constraints of the mouse surface and high-contrast organs (bone and lung). Then the organ probability map of the low-contrast organs, such as the liver and kidney, is determined automatically. After discretization of the mouse torso, a heterogeneous model is established as the input for reconstruction, in which the optical parameter of each node is calculated according to the organ probability map. To take the advantage of the sparse Bayesian Learning (SBL) method in recovering block sparse signals in inverse problems, which is common in BLT applications where the target distribution has the characteristic of sparsity and block structure, a two-step method in conjunction with the organ probability map is presented. In the first step, a fast sparse algorithm, L1-LS, is used to reveal the source distribution on the organ level. In the second step, the bioluminescent source is reconstructed on the pixel level based on the SBL method. Both simulation and in vivo experiments are conducted, and the results demonstrate that the organ probability map in conjunction with the proposed two-step BLT reconstruction method is feasible to accurately reconstruct the localization of the bioluminescent light source.