Bioluminescence tomography (BLT) is used to localize and quantify bioluminescent sources in a small living animal. By advancing bioluminescent imaging to a tomographic framework, it helps to diagnose diseases, monitor therapies and facilitate drug development. In this paper, we establish a direct linear relationship between measured surface photon density and an unknown bioluminescence source distribution by using a finite-element method based on the diffusion approximation to the photon propagation in biological tissue. We develop a novel reconstruction algorithm to recover the source distribution. This algorithm incorporates a priori knowledge to define the permissible source region in order to enhance numerical stability and efficiency. Simulations with a numerical mouse chest phantom demonstrate the feasibility of the proposed BLT algorithm and reveal its performance in terms of source location, density, and robustness against noise. Lastly, BLT experiments are performed to identify the location and power of two light sources in a physical mouse chest phantom.

Motivated by bioluminescent imaging needs for studies on gene therapy and other applications in the mouse models, a bioluminescence tomography (BLT) system is being developed in the University of Iowa. While the forward imaging model is described by the well-known diffusion equation, the inverse problem is to recover an internal bioluminescent source distribution subject to Cauchy data. The primary goal of this paper is to establish the solution uniqueness for BLT under practical constraints despite the illposedness of the inverse problem in the general case.After a review on the inverse source literature, we demonstrate that in the general case the BLT solution is not unique by constructing the set of all the solutions to this inverse problem. Then, we show the uniqueness of the solution in the case of impulse sources. Finally, we present our main theorem that solid/hollow ball sources can be uniquely determined up to non-radiating sources. For better readability, the exact conditions for and rigorous proofs of the theorems are given in the appendices. Further research directions are also discussed. Index TermsBioluminescence tomography (BLT), diffusion equation, inverse source problem, solution uniqueness.

A heterogeneous information network is a network composed of multiple types of objects and links. Recently, it has been recognized that strongly-typed heterogeneous information networks are prevalent in the real world. Sometimes, label information is available for some objects. Learning from such labeled and unlabeled data via transductive classification can lead to good knowledge extraction of the hidden network structure. However, although classification on homogeneous networks has been studied for decades, classification on heterogeneous networks has not been explored until recently.In this paper, we consider the transductive classification problem on heterogeneous networked data which share a common topic. Only some objects in the given network are labeled, and we aim to predict labels for all types of the remaining objects. A novel graph-based regularization framework, GNetMine, is proposed to model the link structure in information networks with arbitrary network schema and arbitrary number of object/link types. Specifically, we explicitly respect the type differences by preserving consistency over each relation graph corresponding to each type of links separately. Efficient computational schemes are then introduced to solve the corresponding optimization problem. Experiments on the DBLP data set show that our algorithm significantly improves the classification accuracy over existing state-of-theart methods.ii To my family for all their love.iii

Abstract-This paper investigates the problem of speaker identification and verification in noisy conditions, assuming that speech signals are corrupted by environmental noise, but knowledge about the noise characteristics is not available. This research is motivated in part by the potential application of speaker recognition technologies on handheld devices or the Internet. While the technologies promise an additional biometric layer of security to protect the user, the practical implementation of such systems faces many challenges. One of these is environmental noise. Due to the mobile nature of such systems, the noise sources can be highly time-varying and potentially unknown. This raises the requirement for noise robustness in the absence of information about the noise. This paper describes a method that combines multicondition model training and missing-feature theory to model noise with unknown temporal-spectral characteristics. Multicondition training is conducted using simulated noisy data with limited noise variation, providing a "coarse" compensation for the noise, and missing-feature theory is applied to refine the compensation by ignoring noise variation outside the given training conditions, thereby reducing the training and testing mismatch. This paper is focused on several issues relating to the implementation of the new model for real-world applications. These include the generation of multicondition training data to model noisy speech, the combination of different training data to optimize the recognition performance, and the reduction of the model's complexity. The new algorithm was tested using two databases with simulated and realistic noisy speech data. The first database is a redevelopment of the TIMIT database by rerecording the data in the presence of various noise types, used to test the model for speaker identification with a focus on the varieties of noise. The second database is a handheld-device database collected in realistic noisy conditions, used to further validate the model for real-world speaker verification. The new model is compared to baseline systems and is found to achieve lower error rates.

It has been recently recognized that heterogeneous information networks composed of multiple types of nodes and links are prevalent in the real world. Both classification and ranking of the nodes (or data objects) in such networks are essential for network analysis. However, so far these approaches have generally been performed separately. In this paper, we combine ranking and classification in order to perform more accurate analysis of a heterogeneous information network. Our intuition is that highly ranked objects within a class should play more important roles in classification. On the other hand, class membership information is important for determining a quality ranking over a dataset. We believe it is therefore beneficial to integrate classification and ranking in a simultaneous, mutually enhancing process, and to this end, propose a novel ranking-based iterative classification framework, called RankClass. Specifically, we build a graph-based ranking model to iteratively compute the ranking distribution of the objects within each class. At each iteration, according to the current ranking results, the graph structure used in the ranking algorithm is adjusted so that the subnetwork corresponding to the specific class is emphasized, while the rest of the network is weakened. As our experiments show, integrating ranking with classification not only generates more accurate classes than the state-of-art classification methods on networked data, but also provides meaningful ranking of objects within each class, serving as a more informative view of the data than traditional classification.

No abstract

Abstract:The bioluminescence tomography is a novel molecular imaging technology for small animal studies. Known reconstruction methods require the completely measured data on the external surface, although only partially measured data is available in practice. In this work, we formulate a mathematical model for BLT from partial data and generalize our previous results on the solution uniqueness to the partial data case. Then we extend two of our reconstruction methods for BLT to this case. The first method is a variant of the well-known EM algorithm. The second one is based on the Landweber scheme. Both methods allow the incorporation of knowledgebased constraints. Two practical constraints, the source non-negativity and support constraints, are introduced to regularize the BLT problem and produce stability. The initial choice of both methods and its influence on the regularization and stability are also discussed. The proposed algorithms are evaluated and validated with intensive numerical simulation and a physical phantom experiment. Quantitative results including the location and source power accuracy are reported. Various algorithmic issues are investigated, especially how to avoid the inverse crime in numerical simulations.

We introduce a general iterative scheme for image reconstruction based on Landweber's method. In our configuration, a sequential block-iterative (SeqBI) version can be readily formulated from a simultaneous block-iterative (SimBI) version, and vice versa. This provides a mechanism to derive new algorithms from known ones. It is shown that some widely used iterative algorithms, such as the algebraic reconstruction technique (ART), simultaneous ART (SART), Cimmino's, and the recently designed diagonal weighting and component averaging algorithms, are special examples of the general scheme. We prove convergence of the general scheme under conditions more general than assumed in earlier studies, for its SeqBI and SimBI versions in the consistent and inconsistent cases, respectively. Our results suggest automatic relaxation strategies for the SeqBI and SimBI versions and characterize the dependence of the limit image on the initial guess. It is found that in all cases the limit is the sum of the minimum norm solution of a weighted least-squares problem and an oblique projection of the initial image onto the null space of the system matrix.