Low-dose-rate prostate brachytherapy treatment takes place by implantation of small radioactive seeds in and sometimes adjacent to the prostate gland. A patient specific target anatomy for seed placement is usually determined by contouring a set of collected transrectal ultrasound images prior to implantation. Standard-of-care in prostate brachytherapy is to delineate the clinical target anatomy, which closely follows the real prostate boundary. Subsequently, the boundary is dilated with respect to the clinical guidelines to determine a planning target volume. Manual contouring of these two anatomical targets is a tedious task with relatively high observer variability. In this work, we aim to reduce the segmentation variability and planning time by proposing an efficient learning-based multi-label segmentation algorithm. We incorporate a sparse representation approach in our methodology to learn a dictionary of sparse joint elements consisting of images, and clinical and planning target volume segmentation. The generated dictionary inherently captures the relationships among elements, which also incorporates the institutional clinical guidelines. The proposed multi-label segmentation method is evaluated on a dataset of 590 brachytherapy treatment records by 5-fold cross validation. We show clinically acceptable instantaneous segmentation results for both target volumes.

A single-task functional magnetic resonance imaging (fMRI) experiment may only partially highlight alterations to functional brain networks affected by a particular disorder. Multivariate analysis across multiple fMRI tasks may increase the sensitivity of fMRI-based diagnosis. Prior research using multi-task analysis in fMRI, such as those that use joint independent component analysis (jICA), has mainly assumed that brain activity patterns evoked by different tasks are independent. This may not be valid in practice. Here, we use sparsity, which is a natural characteristic of fMRI data in the spatial domain, and propose a joint sparse representation analysis (jSRA) method to identify common information across different functional subtraction (contrast) images in data from a multi-task fMRI experiment. Sparse representation methods do not require independence, or that the brain activity patterns be nonoverlapping. We use functional subtraction images within the joint sparse representation analysis to generate joint activation sources and their corresponding sparse modulation profiles. We evaluate the use of sparse representation analysis to capture individual differences with simulated fMRI data and with experimental fMRI data. The experimental fMRI data was acquired from 16 young (age: 19-26) and 16 older (age: 57-73) adults obtained from multiple speech comprehension tasks within subjects, where an independent measure (namely, age in years) can be used to differentiate between groups. Simulation results show that this method yields greater sensitivity, precision, and higher Jaccard indexes (which measures similarity and diversity of the true and estimated brain activation sources) than does the jICA method. Moreover, superiority of the jSRA method in capturing individual differences was successfully demonstrated using experimental fMRI data.

We propose a method for the analysis of brain structural data to simultaneously identify differences in position, orientation and size (i.e. pose), and in shape of multiple brain regions between young people with, and without, a depressive disorder. Different structures in both hemispheres of the brain of depressed and control participants were segmented and corresponding points on the surface of each structure were extracted. Coordinates of these surface points were used to obtain shape variations, and parameters of similarity transformations between brain structures across subjects were used to generate pose variations. Since these surface points and similarity transformations form Lie groups, a logarithmic mapping of members of the Lie groups was performed to transform them to a linear tangent space. Then, Independent Component Analysis (ICA) was used to obtain the independent sources of pose and shape variations on Lie group members, and their corresponding modulation profiles. A method for ordering the independent sources is proposed. The top ordered sources were used to detect pose and shape differences between the two groups, and confirm that even in their first depressive episode, the brains of depressed adolescents differ structurally from the brains of their nondepressed age- and sex-matched peers.

The i.i.d. duplication channel which duplicates each symbol independently with a certain probability is studied. The contribution is twofold: first, a tight lower bound on the capacity of such channels is introduced. Second, the capacity is computed for the small values of the duplication probability using a series expansion representation.

A new adaptive steganography method based on image contrast to improve the embedding capacity and imperceptibility of the stego images is presented. The method exploits the average difference between the gray level values of the pixels in 2×2 blocks of non-overlapping spatially and their mean gray level in order to select valid blocks for embedding. The method was tested on different gray scale images. Results show that our proposed approach provides larger embedding capacity, while being less detectable by steganalysis methods such as ¿2 attack and machine learning steganalysis systems, as compared to some well-known adaptive and non-adaptive steganography algorithms.

In this study, a new feature-based steganalytic method is presented and four classification methods: Fisher linear discriminant, Gaussian naive Bayes, multilayer perceptron, and k nearest neighbor, are compared for steganalysis of suspicious images. The method exploits statistics of the histogram, wavelet statistics, amplitudes of local extrema from the ID and 2D adjacency histograms, center of mass of the histogram characteristic function and co-occurrence matrices for feature extraction process. In order to reduce the proposed features dimension and select the best subset, genetic algorithm is used and the results are compared through principle component analysis and linear discriminant analysis. The results show that the proposed method achieves higher accuracy in discriminating between innocent and stego images, as compared to one of wellknown image steganalysis schemes.

Receive antenna selection for unitary space-time modulation (USTM) over semi-correlated Ricean fading channels is analyzed (this work generalizes that of Ma and Tepedelenlio-glu for the independent and identically distributed (i.i.d.) Rayleigh fading case). The antenna selection rule is that the receive antennas with the largest signal powers are chosen. For single antenna selection, we derive the maximum likelihood decoding for the correlated Ricean case. We also derive the Chernoff bound on the pairwise error probability for the high signal to- noise ratio (SNR) region and obtain the coding gain and diversity order. Our results show that even when there are transmitter side correlations and a line of sight component, receive antenna selection with USTM preserves the full diversity order if the USTM constellation is of full rank. We also give an approximation to the distribution function of a quadratic form of non-zero mean complex Gaussian variates (from Nabar et al.) at the high SNR region. Based on this approximation, a closed-form expression for the coding gain is also obtained and compared with that of the i.i.d. Rayleigh case. We also analyze the case of multiple receive antenna selection and derive the coding gain and diversity order. We show that USTM constellations, which have been proposed for the i.i.d. Rayleigh channel, can be used with the correlated Ricean channel as well.

Low-density parity-check (LDPC) codes have been used for communication over a two-user Gaussian broadcast channel. It has been shown in the literature that the optimal decoding of such system requires joint decoding of both user messages at each user. Also, a joint code design procedure should be performed. We propose a method which uses a novel labeling strategy and is based on the idea behind the bit-interleaved coded modulation. This method does not require joint decoding and/or joint code optimization. Thus, it reduces the overall complexity of near-capacity coding in broadcast channels. For different rate pairs on the boundary of the capacity region, pairs of LDPC codes are designed to demonstrate the success of this technique.

Design of low-density parity-check (LDPC) codes suitable for all channels which exhibit a given capacityCis investigated. Such codes are referred to as universal LDPC codes. First, based on numerous observations, a conjecture is put forth that a code working onNequal-capacity channels, also works on any convex combination of theseNchannels. As a supporting evidence, we prove that a code satisfying the stability condition onNchannels, also satisfies the stability condition on the convex hull of theseNchannels. Then, a channel decomposition method is suggested which spans any given channel with capacityCin terms of a number of identical-capacity basis channels. We expect codes that work on the basis channels to be suitable for any convex combination of the bases, i.e., all channels with capacityC. Such codes are found over a wide range of rates. An upper bound on the achievable rate of universal LDPC codes is suggested. Through examples, it is shown that our codes achieve rates extremely close to this upper bound. In comparison with existing LDPC codes designed for a given channel, significant performance gain is reported when codes are used over various channels of equal capacity.

Low-density parity-check (LDPC) coding for a multitude of equal-capacity channels is studied. First, based on numerous observations, a conjecture is stated that when the belief propagation decoder converges on a set of equal-capacity channels, it would also converge on any convex combination of those channels. Then, it is proved that when the stability condition is satisfied for a number of channels, it is also satisfied for any channel in their convex hull. For the purpose of code design, a method is proposed which can decompose every symmetric channel with capacity C into a set of identical-capacity basis channels. We expect codes that work on the basis channels to be suitable for any channel with capacity C. Such codes are found and in comparison with existing LDPC codes that are designed for specific channels, our codes obtain considerable coding gains when used across a multitude of channels.