Local Connectivity Information Research Articles

Abstract WP16: Automated Vessel Identification In The Circle Of Willis Using Deep Learning Models To Assist AI Based Lesion Detection In Cerebral Vasculature

Introduction: Vascular diseases are among the top causes of death in the world. Automated approaches which allow comparison of vasculature enable both large population studies of vasculature and assist objective diagnosis of vascular disease. Accurate and robust methods for vessel labeling of angiography are an important step to automatically localize lesions or other features of interest. Hypothesis: using a deep learning approach, a model can be developed to identify cerebral arteries. Methods: We used 152 cerebral TOF-MRA angiograms from three publicly available datasets and automatically segmented vessels using a pre-trained nnU-net model. With the segmented vessels, we manually created reference labels for different cerebral arteries using 3DSlicer. After extracting vessel centerlines from the segmentations using VesselVio, we then associated each centerline point with the reference labels to assign individual arterial segments. Finally, in an ablation-type study, several PointNet++ point cloud models were trained and evaluated, using the centerline coordinates, local vessel radius and/or centerline point connectivity information as inputs. Results: The model trained only on centerline coordinates resulted in a high true positive rate (TPR) of 0.92, while models trained with additional features resulted in significantly higher (p<0.05) TPR of 0.95. Different PointNet++ models favored improved labeling of certain arteries, while the internal carotid artery, and posterior communicating artery were consistently the most and least accurately labeled arteries, respectively. Conclusion: We developed a complete pipeline utilizing a deep learning PointNet++ for automatic cerebral vessel identification that labels vessels based on automatically extracted centerlines. Results show that utilizing vessel radius as an additional feature significantly improved cerebral vasculature labeling. The overall TPR of 0.95 shows that our model can be used for fast and reliable artery labeling of cerebral MRA images.

Detection of influential nodes with multi-scale information* *Project supported by the National Natural Science Foundation of China (Grant Nos. 11801430, 11801200, 61877046, and 61877047).

The identification of influential nodes in complex networks is one of the most exciting topics in network science. The latest work successfully compares each node using local connectivity and weak tie theory from a new perspective. We study the structural properties of networks in depth and extend this successful node evaluation from single-scale to multi-scale. In particular, one novel position parameter based on node transmission efficiency is proposed, which mainly depends on the shortest distances from target nodes to high-degree nodes. In this regard, the novel multi-scale information importance (MSII) method is proposed to better identify the crucial nodes by combining the network’s local connectivity and global position information. In simulation comparisons, five state-of-the-art algorithms, i.e. the neighbor nodes degree algorithm (NND), betweenness centrality, closeness centrality, Katz centrality and the k-shell decomposition method, are selected to compare with our MSII. The results demonstrate that our method obtains superior performance in terms of robustness and spreading propagation for both real-world and artificial networks.

A self-localization range free protocol for wireless sensor networks

Wireless Sensor Networks (WSNs) attract a large variety of applications. The physical localization of sensors is one of the fundamental tasks in such networks. This task is challenging due to technical and financial constraints of nodes that need sophisticated solutions. Existing satellite-based methods might be cost, require high-energy consumption with no guarantee of full coverage of that area. Therefore, other methods, which use the local connectivity information to deduce sensors position, provide an approximate or a relative localization. In this work, we propose a new localization protocol called SL-Free protocol (Self Localization protocol based range-free), which provides a fine localization for node. The main goal of this proposal is to give the most precised coordinates with less cost. The performance study shows that, SL-Free outperforms its peers in terms of precision and energy use.

Node classification using kernel propagation in graph neural networks

In this work, we introduce a kernel propagation method that enables graph neural networks (GNNs) to leverage higher-order network structural information without increasing the complexity of the networks. Recent studies have introduced GNNs that include higher-order neighborhood features containing global network information by propagating node features using a higher-order feature propagation rule. Though these GNNs have shown to improve node classification performance, they fail to include local connectivity information. Alternatively, GNNs also concatenate increasing orders of adjacency matrix in deeper layers in order to include higher-order structural information. In addition to global network information, GNNs also make use of node features which are network and node dependent features that serve to distinguish structurally isomorphic sub-structures within graphs. However, such node features may not always be available or depending on the network, may lead to deteriorating classification performance. Hence, to resolve these limitations, we propose a kernel propagation method that introduces a pre-processing step for GNNs to leverage higher-order structural features. The higher-order structural features are computed using a weighted random walk matrix which is node independent while using the first-order spectral propagation rule which explicitly considers local connectivity. Through our benchmark experiments, we find that the computed higher-order structural features are capable of replacing node dependent features while performing node classification task with performance on par with the state of the art approaches. Further, we also find that including both node features and higher-order structural features increases the performance of GNNs on large scale benchmark networks considered in this study. Our results show that considering local and global structural information as input to GNNs lead to an improvement in node classification performance in the absence/presence of node features without loss of performance.

Depth-based subgraph convolutional auto-encoder for network representation learning

Network representation learning (NRL) aims to map vertices of a network into a low-dimensional space which preserves the network structure and its inherent properties. Most existing methods for network representation adopt shallow models which have relatively limited capacity to capture highly non-linear network structures, resulting in sub-optimal network representations. Therefore, it is nontrivial to explore how to effectively capture highly non-linear network structure and preserve the global and local structure in NRL. To solve this problem, in this paper we propose a new graph convolutional autoencoder architecture based on a depth-based representation of graph structure, referred to as the depth-based subgraph convolutional autoencoder (DS-CAE), which integrates both the global topological and local connectivity structures within a graph. Our idea is to first decompose a graph into a family of K-layer expansion subgraphs rooted at each vertex aimed at better capturing long-range vertex inter-dependencies. Then a set of convolution filters slide over the entire sets of subgraphs of a vertex to extract the local structural connectivity information. This is analogous to the standard convolution operation on grid data. In contrast to most existing models for unsupervised learning on graph-structured data, our model can capture highly non-linear structure by simultaneously integrating node features and network structure into network representation learning. This significantly improves the predictive performance on a number of benchmark datasets.

Utilizing networks for differential analysis of chromatin interactions.

Chromatin conformation capture with high-throughput sequencing (Hi-C) is a powerful technique to detect genome-wide chromatin interactions. In this paper, we introduce two novel approaches to detect differentially interacting genomic regions between two Hi-C experiments using a network model. To make input data from multiple experiments comparable, we propose a normalization strategy guided by network topological properties. We then devise two measurements, using local and global connectivity information from the chromatin interaction networks, respectively, to assess the interaction differences between two experiments. When multiple replicates are present in experiments, our approaches provide the flexibility for users to either pool all replicates together to therefore increase the network coverage, or to use the replicates in parallel to increase the signal to noise ratio. We show that while the local method works better in detecting changes from simulated networks, the global method performs better on real Hi-C data. The local and global methods, regardless of pooling, are always superior to two existing methods. Furthermore, our methods work well on both unweighted and weighted networks and our normalization strategy significantly improves the performance compared with raw networks without normalization. Therefore, we believe our methods will be useful for identifying differentially interacting genomic regions.

Rasterized Planar Face Complex

We consider a Planar Face Complex (PFC). It is defined by the immersion of a planar and connected graph G, which comprises a set of vertices joined by curved edges. G decomposes the plane into faces that need not be manifold or open-regularized and may be bounded by a single loop edge. The PFC may, for example, be used to represent the complex street network of a city, the decomposition of a continent into countries, or the inhomogeneous structure made of a large set of regions of different materials possibly with internal cracks. The rasterized Planar Face Complex (rPFC) proposed here provides a compact representation of an approximation of a PFC, where the precise location of each vertex is quantized to the pixel that contains it and where the precise geometry of each curved edge is approximated by the ordered list (with possible repetitions) of the pixels traversed by (a chosen polygonal approximation of) the edge. We claim three key contributions: (1) The geometric error between a PFC and its rPFC is bounded by the pixel half-diagonal. (2) In spite of such a drastic discretization of the geometry, the rPFC captures the exact topology of the original PFC (provided that no street lies entirely inside a single pixel) and supports standard graph traversal operators that permit to walk the loop of sidewalks along the streets that bound a face, to cross a street to the opposite sidewalk, or to cross streets in order while walking around their common junction. (3) The local connectivity and order information needed to provide the above functionality is stored at each pixel using only about 4 bits per crossing. We discuss the details of this representation, our implementation of its exact construction, four possible embodiments that offer different space/time efficiency compromises, experimental results, relations between rPFC and prior solutions.

Group-wise parcellation of the cortex through multi-scale spectral clustering

The delineation of functionally and structurally distinct regions as well as their connectivity can provide key knowledge towards understanding the brain's behaviour and function. Cytoarchitecture has long been the gold standard for such parcellation tasks, but has poor scalability and cannot be mapped in vivo. Functional and diffusion magnetic resonance imaging allow in vivo mapping of brain's connectivity and the parcellation of the brain based on local connectivity information. Several methods have been developed for single subject connectivity driven parcellation, but very few have tackled the task of group-wise parcellation, which is essential for uncovering group specific behaviours. In this paper, we propose a group-wise connectivity-driven parcellation method based on spectral clustering that captures local connectivity information at multiple scales and directly enforces correspondences between subjects. The method is applied to diffusion Magnetic Resonance Imaging driven parcellation on two independent groups of 50 subjects from the Human Connectome Project. Promising quantitative and qualitative results in terms of information loss, modality comparisons, group consistency and inter-group similarities demonstrate the potential of the method.

Pascal’s triangle-based range-free localization for anisotropic wireless networks

This paper introduces a Pascal's triangle model to draw the potential locations and their probabilities for a normal node given the hop counts to the anchors according to the extent of detour of the shortest paths. Based on our proposed model, a Pascal's triangle-based localization (PTL) algorithm using local connectivity information is presented for anisotropic wireless networks with a small number of anchors. The superiority of the PTL algorithm has been validated over the state-of-the-art algorithms through MATLAB simulations. We have shown that compared to the other algorithms, the PTL algorithm achieves higher localization accuracy with even fewer anchors. We have also validated the performance of the PTL algorithm in a real environment.

Energy Optimization in Manets Using On-demand Routing Protocol

Mobile Ad hoc networks (MANET) allow a set of wireless hosts to exchange information without any special infrastructure. The projct entitled “Energy Optimization in Manets using On-Demand Routing Protocol” motivates the need for energy management in ad hoc wireless networks. Limited battery power is one of the most important issues in mobile ad hoc network as the mobile nodes operate in limited battery power. Also there occurs a problem of broken links due to the lack of energy which cause disorder in network system. Such problem occurs due to the unawareness of energy of mobile neighbor nodes. This paper presents the implementation of Adaptive HELLO messaging scheme to determine the local link connectivity information for monitoring the link status between nodes along with the incorporation of Dynamic On Demand Routing Protocol to reduce the energy consumption of mobile nodes to certain extent.

Recognizing Boundaries in Wireless Sensor Networks Based on Local Connectivity Information

This paper develops an efficient and distributed boundary detection algorithm to precisely recognize wireless sensor network (WSN) boundaries using only local connectivity information. Specifically, given any node in a WSN, the proposed algorithm constructs its 2-hop isocontour and locally makes a rough decision on whether this node is suspected to be on boundaries of the WSN by examining the associated 2-hop isocontour. Then, a heuristic operation is performed to refine this decision, with the result that the suspected boundary node set is significantly shrunk. Lastly, tight boundary cycles corresponding to both inner and outer WSN boundaries are derived by searching the suspected boundary node set. Furthermore, regarding WSNs with relatively low node densities, the proposed algorithm is adapted to improve the quality of boundary detection. Even though the proposed algorithm is initially presented under the assumption of the idealized unit disk graph (UDG) model, we further consider the more realistic quasi-UDG (QUDG) model. In addition, a message complexity analysis confirms the energy efficiency of the proposed algorithm. Finally, we carry out a thorough evaluation showing that our algorithm is applicable to both dense and sparse deployments of WSNs and is able to produce accurate results.

An Adaptive Hello Messaging Scheme for Neighbor Discovery in On-Demand MANET Routing Protocols

In mobile ad-hoc networks, local link connectivity information is extremely important for route establishment and maintenance. Periodic Hello messaging is a widely-used scheme to obtain local link connectivity information. However, unnecessary Hello messaging can drain batteries while mobile devices are not in use. This paper proposes an adaptive Hello messaging scheme to suppress unnecessary Hello messages without reduced detectability of broken links. Simulation results show that the proposed scheme reduces energy consumption and network overhead without any explicit difference in throughput.

Fine-Grained Location-Free Planarization in Wireless Sensor Networks

Extracting planar graph from network topologies is of great importance for efficient protocol design in wireless ad hoc and sensor networks. Previous techniques of planar topology extraction are often based on ideal assumptions, such as UDG communication model and accurate node location measurements. To make these protocols work effectively in practice, we need extract a planar topology in a location-free and distributed manner with small stretch factors. The planar topologies constructed by current location-free methods often have large stretch factors. In this paper, we present a fine-grained and location-free network planarization method under ρ-quasi-UDG communication model with ρ≥1/√2. Compared with existing location-free planarization approaches, our method can extract a provably connected planar graph, called topological planar simplification (TPS), from the connectivity graph in a fine-grained manner using local connectivity information. We evaluate our design through extensive simulations and compare with the state-of-the-art approaches. The simulation results show that our method produces high-quality planar graphs with a small stretch factor in practical large-scale networks.

비등방성 센서 네트워크에서 가상 홀을 이용한 다중 홉 Range-Free 측위 알고리즘

This paper presents a multihop range-free localization algorithm to estimate the physical location of a normal node with local connectivity information in anisotropic sensor networks. In the proposed algorithm, a normal node captures the detour degree of the shortest path connecting an anchor pair and itself by comparing the measured hop count and the expected hop count, and the node estimates the distances to the anchors based on the detour degree. The normal node repeats this procedure with all anchor combinations and pinpoints its location using the obtained distance estimates. The proposed algorithm requires fewer anchors and less communication overhead compared to existing range-free algorithms. We showed the superiority of the proposed algorithm over existing range-free algorithms through MATLA simulations.

White matter structural connectivity is associated with sensorimotor function in stroke survivors

PurposeDiffusion tensor imaging (DTI) provides functionally relevant information about white matter structure. Local anatomical connectivity information combined with fractional anisotropy (FA) and mean diffusivity (MD) may predict functional outcomes in stroke survivors. Imaging methods for predicting functional outcomes in stroke survivors are not well established. This work uses DTI to objectively assess the effects of a stroke lesion on white matter structure and sensorimotor function.MethodsA voxel-based approach is introduced to assess a stroke lesion's global impact on motor function. Anatomical T1-weighted and diffusion tensor images of the brain were acquired for nineteen subjects (10 post-stroke and 9 age-matched controls). A manually selected volume of interest was used to alleviate the effects of stroke lesions on image registration. Images from all subjects were registered to the images of the control subject that was anatomically closest to Talairach space. Each subject's transformed image was uniformly seeded for DTI tractography. Each seed was inversely transformed into the individual subject space, where DTI tractography was conducted and then the results were transformed back to the reference space. A voxel-wise connectivity matrix was constructed from the fibers, which was then used to calculate the number of directly and indirectly connected neighbors of each voxel. A novel voxel-wise indirect structural connectivity (VISC) index was computed as the average number of direct connections to a voxel's indirect neighbors. Voxel-based analyses (VBA) were performed to compare VISC, FA, and MD for the detection of lesion-induced changes in sensorimotor function. For each voxel, a t-value was computed from the differences between each stroke brain and the 9 controls. A series of linear regressions was performed between Fugl-Meyer (FM) assessment scores of sensorimotor impairment and each DTI metric's log number of voxels that differed from the control group.ResultsCorrelation between the logarithm of the number of significant voxels in the ipsilesional hemisphere and total Fugl-Meyer score was moderate for MD (R2 = 0.512), and greater for VISC (R2 = 0.796) and FA (R2 = 0.674). The slopes of FA (p = 0.0036), VISC (p = 0.0005), and MD (p = 0.0199) versus the total FM score were significant. However, these correlations were driven by the upper extremity motor component of the FM score (VISC: R2 = 0.879) with little influence of the lower extremity motor component (FA: R2 = 0.177).ConclusionThe results suggest that a voxel-wise metric based on DTI tractography can predict upper extremity sensorimotor function of stroke survivors, and that supraspinal intraconnectivity may have a less dominant role in lower extremity function.

MDS-Based Wormhole Detection Using Local Topology in Wireless Sensor Networks

Wormhole attack is a severe threat to wireless sensor networks (WSNs), which has received considerable attentions in the literature. However, most of the previous approaches either require special hardware devices or depend on rigorous assumptions on the network settings, which greatly limit their applicability. In this work, we attempt to relax the limitations in prior work, and propose a novel approach to detect wormhole attacks by only local topology information in WSNs. The basic idea is as follows. Each node locally collects its neighborhood information and reconstructs the neighborhood subgraph by multidimensional scaling (MDS). Potential wormhole nodes are detected by validating the legality of the reconstruction. Then, a refinement process is introduced to filter the suspect nodes and to remove false positives. Our approach solely relies on the local connectivity information and is extremely simple and lightweight, which makes it applicable in practical systems. Extensive simulations are conducted, and the results demonstrate the effectiveness and superior performance of our approach.

Neighbor Selection Game in Wireless Ad Hoc Networks

In wireless ad hoc networks, there is no infrastructure to enforce cooperation between nodes. As a result, nodes may act selfishly when running network protocols to conserve their energy resources as much as possible. In this paper, we consider the "neighbor selection" game in which each individual node tries to selfishly choose its neighborhood such that its own energy consumption is optimized. We first focus on a simplified version of this game where nodes know their transmission power before participating in the game. After analyzing the problem, we propose a couple of distributed algorithms to find stable topologies using two kinds of global and local connectivity information. We then take into account the general case where the transmission powers are unknown variables and should be determined during the game. Finally, we evaluate the performance of the proposed algorithms through simulations.

Estimating distances via connectivity in wireless sensor networks

ABSTRACTDistance estimation is vital for localization and many other applications in wireless sensor networks. In this paper, we develop a method that employs a maximum‐likelihood estimator to estimate distances between a pair of neighboring nodes in a static wireless sensor network using their local connectivity information, namely the numbers of their common and non‐common one‐hop neighbors. We present the distance estimation method under a generic channel model, including the unit disk (communication) model and the more realistic log‐normal (shadowing) model as special cases. Under the log‐normal model, we investigate the impact of the log‐normal model uncertainty; we numerically evaluate the bias and standard deviation associated with our method, which show that for long distances our method outperforms the method based on received signal strength; and we provide a Cramér–Rao lower bound analysis for the problem of estimating distances via connectivity and derive helpful guidelines for implementing our method. Finally, on implementing the proposed method on the basis of measurement data from a realistic environment and applying it in connectivity‐based sensor localization, the advantages of the proposed method are confirmed. Copyright © 2012 John Wiley & Sons, Ltd.

Energy-efficient topology control in wireless ad hoc networks with selfish nodes

In wireless ad hoc networks there is no fixed infrastructure or centralized controller to enforce cooperation between nodes. Therefore, nodes may act selfishly in running network protocols for conserving their own energy resources. In this paper, we consider the “topology control (TC) game” as the problem of creating an energy-efficient topology in wireless ad hoc networks in the presence of selfish nodes. We define a new TC game in which nodes are able to dynamically adjust their transmission power in a per-packet manner, and try to minimize their energy usage through considering both traffic load and transmission power parameters. After analyzing the problem, we propose several algorithms to find stable topologies in an environment composed of selfish nodes, using two types of global and local connectivity information. Finally, we evaluate the performance of the proposed algorithms by simulations. Our simulation results show that using appropriate local information can interestingly result in more efficient topologies than global information.

New measures for characterizing the significance of nodes in wireless ad hoc networks via localized path-based neighborhood analysis

The synergy between social network analysis and wireless ad hoc network protocol design has recently created increased interest for developing methods and measures that capture the topological characteristics of a wireless network. Such techniques are used for the design of routing and multicasting protocols, for cooperative caching purposes and so on. These techniques are mandatory to characterize the network topology using only limited, local connectivity information—one or two hop information. Even though it seems that such techniques can straightforwardly be derived from the respective network-wide techniques, their design presents significant challenges since they must capture rich information using limited knowledge. This article examines the issue of finding the most central nodes in neighborhoods of a given network with directed or undirected links taking into account only localized connectivity information. An algorithm that calculates the ranking, taking into account the N-hop neighborhood of each node is proposed. The method is compared to popular existing schemes for ranking, using Spearman’s rank correlation coefficient. An extended, faster algorithm which reduces the size of the examined network is also described.