Hierarchical Labels Research Articles

Multi-Atlas-based Segmentation with Hierarchical Max-Flow

This study investigates a method for brain tissue segmentation from 3D T1 weighted (T1w) MR images via convex relaxation with a hierarchical ordering constraint. It employs a multi-atlas-based initialization from 5 training images and is tested on 12 T1w MR images provided by the MICCAI 2013 MRBrainS segmentation challenge. The registered atlas images, fully segmented into eight different brain structures, are used to formulate shape and intensity priors for a Maximum A-Posteriori (MAP) energy that is subsequently minimized with a dual hierarchical max-flow computation. The algorithm makes use of a hierarchical label ordering constraint to regularize label families individually and its inherently globally optimal results guarantee robust segmentations. Major parts of the image processing pipeline are implemented using General-Purpose Programming on Graphics Processing Units (GPGPU) for a substantial increase in computation speed.

Sparse Patch-Based Label Propagation for Accurate Prostate Localization in CT Images

In this paper, we propose a new prostate computed tomography (CT) segmentation method for image guided radiation therapy. The main contributions of our method lie in the following aspects. 1) Instead of using voxel intensity information alone, patch-based representation in the discriminative feature space with logistic sparse LASSO is used as anatomical signature to deal with low contrast problem in prostate CT images. 2) Based on the proposed patch-based signature, a new multi-atlases label fusion method formulated under sparse representation framework is designed to segment prostate in the new treatment images, with guidance from the previous segmented images of the same patient. This method estimates the prostate likelihood of each voxel in the new treatment image from its nearby candidate voxels in the previous segmented images, based on the nonlocal mean principle and sparsity constraint. 3) A hierarchical labeling strategy is further designed to perform label fusion, where voxels with high confidence are first labeled for providing useful context information in the same image for aiding the labeling of the remaining voxels. 4) An online update mechanism is finally adopted to progressively collect more patient-specific information from newly segmented treatment images of the same patient, for adaptive and more accurate segmentation. The proposed method has been extensively evaluated on a prostate CT image database consisting of 24 patients where each patient has more than 10 treatment images, and further compared with several state-of-the-art prostate CT segmentation algorithms using various evaluation metrics. Experimental results demonstrate that the proposed method consistently achieves higher segmentation accuracy than any other methods under comparison.

Vector space model for patent documents with hierarchical class labels

A vector space model (VSM) composed of selected important features is a common way to represent documents, including patent documents. Patent documents have some special characteristics that make it difficult to apply traditional feature selection methods directly: (a) it is difficult to find common terms for patent documents in different categories; and (b) the class label of a patent document is hierarchical rather than flat. Hence, in this article we propose a new approach that includes a hierarchical feature selection (HFS) algorithm which can be used to select more representative features with greater discriminative ability to present a set of patent documents with hierarchical class labels. The performance of the proposed method is evaluated through application to two documents sets with 2400 and 9600 patent documents, where we extract candidate terms from their titles and abstracts. The experimental results reveal that a VSM whose features are selected by a proportional selection process gives better coverage, while a VSM whose features are selected with a weighted-summed selection process gives higher accuracy.

Improving hierarchical document cluster labels through candidate term selection

One way to organize knowledge and make its search and retrieval easier is to create a structural representation divided by hierarchically related topics. Once this structure is built, it is necessary to find labels for each of the obtained clusters. In many cases the labels must be built using all the terms in the documents of the collection. This paper presents the SeCLAR method, which explores the use of association rules in the selection of good candidates for labels of hierarchical document clusters. The purpose of this method is to select a subset of terms by exploring the relationship among the terms of each document. Thus, these candidates can be processed by a classical method to generate the labels. An experimental study demonstrates the potential of the proposed approach to improve the precision and recall of labels obtained by classical methods only considering the terms which are potentially more discriminative.

Novel methodology to characterize electromagnetic exposure of the brain

Due to the greatly non-uniform field distribution induced in brain tissues by radio frequency electromagnetic sources, the exposure of anatomical and functional regions of the brain may be a key issue in interpreting laboratory findings and epidemiological studies concerning endpoints related to the central nervous system. This paper introduces the Talairach atlas in characterization of the electromagnetic exposure of the brain. A hierarchical labeling scheme is mapped onto high-resolution human models. This procedure is fully automatic and allows identification of over a thousand different sites all over the brain. The electromagnetic absorption can then be extracted and interpreted in every region or combination of regions in the brain, depending on the characterization goals. The application examples show how this methodology enhances the dosimetry assessment of the brain based on results obtained by either finite difference time domain simulations or measurements delivered by test compliance dosimetry systems. Applications include, among others, the detailed dosimetric analysis of the exposure of the brain during cell phone use, improved design of exposure setups for human studies or medical diagnostic and therapeutic devices using electromagnetic fields or ultrasound.

Recognition of Optical Layered Binary Phase Shift Keying Labels Using Coherent Acoustooptic Processor for Hierarchical Photonic Routing

Wavelength-selective optical processing using collinear acoustooptic (AO) switches will be useful in photonic routing systems. We have studied the applications of this processing to optical label recognition in label routers. We propose the recognition of hierarchical routing labels encoded in the binary-phase-shift-keying (BPSK) format using an AO processor consisting of optical delay waveguides and parallel double-stage AO switches. Using wavelength-multiplexed hierarchical labels, simple processing using the AO processor can be realized. The recognition characteristics are analyzed and numerically confirmed by computer simulation.

Hierarchical Mobility Label Based Network: System model and performance analysis

Hierarchical Mobility Label Based Network (H-MLBN) is a new approach to the network layer mobility management problem that relies on MPLS-aware control plane and MPLS-based forwarding plane to provide IP mobility support for IPv4 and IPv6 mobile hosts and routers while being able to ensure optimal traffic delivery between the communicating devices. The hierarchical system is capable of both macro- and micro-mobility support without the use of Mobile IP and its derivatives thus eliminating the user and network facing performance penalties associated with triangular routing and bi-directional tunneling. This paper presents a system model and provides performance analysis for H-MLBN and compares its performance with the Mobile IP based schemes. The results indicate significant performance improvements in the forwarding plane traffic delivery as well as the control plane network update costs.

Arithmetic and Fourier transform for the PYXIS multi-resolution digital Earth model

This paper investigates a multi-resolution digital Earth model called PYXIS, which was developed by PYXIS Innovation Inc. The PYXIS hexagonal grids employ an efficient hierarchical labeling scheme for addressing pixels. We provide a recursive definition of the PYXIS grids, a systematic approach to the labeling, an algorithm to add PYXIS labels, and a discussion of the discrete Fourier transform on PYXIS grids.

Structural Segmentation of Musical Audio by Constrained Clustering

We describe a method of segmenting musical audio into structural sections based on a hierarchical labeling of spectral features. Frames of audio are first labeled as belonging to one of a number of discrete states using a hidden Markov model trained on the features. Histograms of neighboring frames are then clustered into segment-types representing distinct distributions of states, using a clustering algorithm in which temporal continuity is expressed as a set of constraints modeled by a hidden Markov random field. We give experimental results which show that in many cases the resulting segmentations correspond well to conventional notions of musical form. We show further how the constrained clustering approach can easily be extended to include prior musical knowledge, input from other machine approaches, or semi-supervision.

Multi-label large margin hierarchical perceptron

This paper looks into classification of documents that have hierarchical labels and are not restricted to a single label. Previous work in hierarchical classification focuses on the hierarchical perceptron (Hieron) algorithm. Hieron only supports single label learning. We investigate applying several standard multi-label learning techniques to Hieron. We then propose an extension of the algorithm (MultiHieron) that significantly outperforms all previously mentioned techniques. MultiHieron has a new aggregate loss function for multiple labels. Improvement is shown on the Aviation Safety Reporting System (ASRS) flight anomaly database and OntoNews corpus using both at and hierarchical categorisation metrics.

A hierarchical Markovian model for multiscale region-based classification of vector-valued images

We propose a new classification method for vector-valued images, based on: 1) a causal Markovian model, defined on the hierarchy of a multiscale region adjacency tree (MRAT), and 2) a set of nonparametric dissimilarity measures that express the data likelihoods. The image classification is treated as a hierarchical labeling of the MRAT, using a finite set of interpretation labels (e.g., land cover classes). This is accomplished via a noniterative estimation of the modes of posterior marginals (MPM), inspired from existing approaches for Bayesian inference on the quadtree. The paper describes the main principles of our method and illustrates classification results on a set of artificial and remote sensing images, together with qualitative and quantitative comparisons with a variety of pixel-based techniques that follow the Bayesian-Markovian framework either on hierarchical structures or the original image lattice.

Generalized multiprotocol label switching: an overview of signaling enhancements and recovery techniques

Generalized multiprotocol label switching (GMPLS), also referred to as multiprotocol lambda switching, is a multipurpose control plane paradigm that supports not only devices that perform packet switching, but also devices that perform switching in the time, wavelength, and space domains. The development of GMPLS necessitates enhancements to existing IP signaling and routing protocols. We present enhancements to two commonly used IP signaling protocols, RSVP and LDP, to support GMPLS. We illustrate the concept of hierarchical label switched path setup with an example, discuss mechanisms for bidirectional LSP setup, and describe the applications of suggested labels. We also discuss the important problem of protection and restoration in the GMPLS context. Finally, we describe how various recovery mechanisms can be implemented within the GMPLS framework.

Aortic valve mass and sudden blindness.

Knowledge of protein function is necessary for understanding biological systems, but the discovery of new sequences from high-throughput sequencing technologies far outpaces their functional characterization. Beyond the problem of assigning...

Connected component labeling with linear octree

The representation and manipulation of 3D objects are important for applications such as computer graphics, pattern recognition, robotics and medical imaging. As a consequence, a considerable amount of research is being carried out in data structures for 3D representation. Among these structures, the linear octree is a hierarchical pointerless representation, which stores object elements as a list of codes. Several algorithms have been proposed for linear octrees, including computation of topological properties and connected components labeling. In this paper, we are concerned with this last operation. However, the techniques we use are not limited to this case. We first introduce a new search technique, which does not make use of neighbor finding techniques that require the location of a nearest common ancestor. Instead, we use a table of pointers in the list. The computational cost of our algorithm has an order of O( N), where N is the number of elements in the list. The memory requirements of the pointer's table is of order O( n), for an 8 n volume. In the second part of the paper, we come to the connected component labeling. Instead of the usual label using n digits, we use a hierarchical labeling, which creates a tree within each component. Its advantages are threefold. Firstly, we do not use an equivalence table. Secondly, in this particular case, our neighbor finding technique requires only O(1) pointers instead of O( n). But its main feature is a memory requirement of order O( N) for the labels, instead of Θ( n × N).

The Cellular Frame Model for Representation and Aggregation of Knowledge in Image Understanding

AbstractThis paper proposes a computational model of hierarchical labeling based on cellular automaton “Cellular Frame Model.” The model of the objective world is described by defining a set of labels called Cellular Frame used for representing knowledge. The reliability of existence of labels for representation by state equations whose initial conditions are determined by input level patterns is described. The state equations are of the form of local, parallel and iterative operations. The computational process of the state equations is considered as a process of aggregation (based on input label patterns) of label knowledge introduced for model description. In this paper, model describability of Cellular Frame is discussed from two viewpoints: hierarchy of the set of labels, and graphic interpretation of aggregate model. Convergence of labeling is ensured by the fact that the state equations always converge. In addition, several hypotheses have been ascertained by showing examples of models and simulation of labeling processes by state equations.