Progressive multi-atlas label fusion by dictionary evolution

Song, Yantao,Wu, Guorong,Bahrami, Khosro,Sun, Quansen,Shen, Dinggang Elsevier 2017 Medical image analysis Vol.36 No.-

<P><B>Abstract</B></P> <P>Accurate segmentation of anatomical structures in medical images is important in recent imaging based studies. In the past years, multi-atlas patch-based label fusion methods have achieved a great success in medical image segmentation. In these methods, the appearance of each input image patch is first represented by an <I>atlas patch dictionary</I> (in the image domain), and then the latent label of the input image patch is predicted by applying the estimated representation coefficients to the corresponding anatomical labels of the atlas patches in the <I>atlas label dictionary</I> (in the label domain). However, due to the generally large gap between the patch appearance in the <I>image domain</I> and the patch structure in the <I>label domain</I>, the estimated (patch) representation coefficients from the image domain may not be optimal for the final label fusion, thus reducing the labeling accuracy. To address this issue, we propose a novel label fusion framework to seek for the suitable label fusion weights by progressively constructing a dynamic dictionary in a layer-by-layer manner, where the intermediate dictionaries act as a sequence of guidance to steer the transition of (patch) representation coefficients from the image domain to the label domain. Our proposed multi-layer label fusion framework is flexible enough to be applied to the existing labeling methods for improving their label fusion performance, i.e., by extending their single-layer <I>static</I> dictionary to the multi-layer <I>dynamic</I> dictionary. The experimental results show that our proposed progressive label fusion method achieves more accurate hippocampal segmentation results for the ADNI dataset, compared to the counterpart methods using only the single-layer <I>static</I> dictionary.</P> <P><B>Highlights</B></P> <P> <UL> <LI> A progressive multi-atlas label fusion method by deep dictionary evolution is proposed. </LI> <LI> A sequence of intermediate dictionaries was constructed to progressively optimize the weights for label fusion. </LI> <LI> As an extension of the conventional single-layer methods by improving their label fusion performance. </LI> </UL> </P> <P><B>Graphical abstract</B></P> <P>[DISPLAY OMISSION]</P>

LETTER TO THE EDITOR : Gene-Gene Interaction between LCE and CLEC16A Increases the Risk of Psoriasis in a Chinese Population

( Jianbo Wang ),( Yantao Ding ),( Xing Fan ),( Xianbo Zuo ),( Wen Wang ),( Hui Cheng ),( Ping Li ),( Liangdan Sun ),( Sen Yang ),( Xuejun Zhang ) 대한피부과학회 2014 Annals of Dermatology Vol.26 No.3

Datacenter-Oriented Elastic Optical Networks: Architecture, Operation, and Solutions

( Limei Peng ),( Yantao Sun ),( Min Chen ),( Kiejin Park ) 한국인터넷정보학회 2014 KSII Transactions on Internet and Information Syst Vol.8 No.11

With the exponentially increasing Internet traffic and emergence of more versatile and heterogeneous applications, the design of datacenter networks (DCNs) is subject to unprecedented requirements for larger capacity and more flexible switching granularities. Envisioning Optical-Orthogonal Frequency Division Multiplexing (O-OFDM) as a promising candidate for such a scenario, we motivate the use of O-OFDM as the underlying switching technology in order to provide sufficient switching capacity and elastic bandwidth allocation. For this purpose, this article reviews the recent progresses of DCN deployment and assesses the scenario where the O-OFDM transmission and switching technology is employed in the underlying transport plane. We discuss the key issues of the datacenter-oriented O-OFDM optical networks, and in particular, elaborate on a number of open issues and solutions including system interconnection architecture, routing and resource assignment, survivability, and energy-efficiency.

Integration of Wireless Body Area Networks (WBANs) and WAN, WiMAX and LTE

( Long Hu ),( Ong Mau Dung ),( Qiang Liu ),( Tao Han ),( Yantao Sun ) 한국인터넷정보학회 2013 KSII Transactions on Internet and Information Syst Vol.7 No.5

Nowadays, wireless communication has a great advantage in technology. We use wireless devices almost in all expected life such as: entertainment, working and recently in the healthcare area, where Wireless Body Area Networks (WBANs) become a hot topic for researchers and system designers. Recent work on WBANs focus on related issues to communication protocol, especially ZigBee network is fine tuned to meet particular requirements in healthcare area. For example, some papers present real-time patient monitoring via ZigBee communication given the short distance between body sensors and remote devices, while the other work solve the limited coverage problem of Zigbee by designing mechanisms to relay Zigbee data to other types of wire or wireless infrastructure. However, very few of them investigate the scenarios of ZigBee coexisting or integrated with other networks. In this paper, we present the real-time data transmission from ZigBee end devices to Wide Area Network (WAN), Worldwide interoperation for microwave access network (WiMAX) and Long Term Evolution network (LTE). We provide in detail the ZigBee gateway components. Our simulation is conducted by OPNET, we visualize many topology network scenarios in ZigBee hybrid system. The results in simulation show that ZigBee end devices can successfully transmit data in real-time to other network end devices.

SERS study of surface plasmon resonance induced carrier movement in Au@Cu₂O core-shell nanoparticles

Chen, Lei,Zhang, Fan,Deng, Xin-Yu,Xue, Xiangxin,Wang, Li,Sun, Yantao,Feng, Jing-Dong,Zhang, Yongjun,Wang, Yaxin,Jung, Young Mee Elsevier 2018 Spectrochimica acta. Part A, Molecular and biomole Vol.189 No.-

<P><B>Abstract</B></P> <P>A plasmon induced carrier movement enhanced mechanism of surface-enhanced Raman scattering (SERS) was investigated using a charge-transfer (CT) enhancement mechanism. Here, we designed a strategy to study SERS in Au@Cu<SUB>2</SUB>O nanoshell nanoparticles with different shell thicknesses. Among the plasmonically coupled nanostructures, Au spheres with Cu<SUB>2</SUB>O shells have been of special interest due to their ultrastrong electromagnetic fields and controllable carrier transfer properties, which are useful for SERS. Au@Cu<SUB>2</SUB>O nanoshell nanoparticles (NPs) with shell thicknesses of 48–56nm are synthesized that exhibit high SERS activity. This high activity originates from plasmonic-induced carrier transfer from Au@Cu<SUB>2</SUB>O to 4-mercaptobenzoic acid (MBA). The CT transition from the valence band (VB) of Cu<SUB>2</SUB>O to the second excited π-π* transition of MBA, and is of b<SUB>2</SUB> electronic symmetry, which was enhanced significantly. The Herzberg-Teller selection rules were employed to predict the observed enhanced b<SUB>2</SUB> symmetry modes. The system constructed in this study combines the long-range electromagnetic effect of Au NPs, localized surface plasmon resonance (LSPR) of the Au@Cu<SUB>2</SUB>O nanoshell, and the CT contribution to assist in understanding the SERS mechanism based on LSPR-induced carrier movement in metal/semiconductor nanocomposites.</P> <P><B>Highlights</B></P> <P> <UL> <LI> We designed a shell-dependent Au@Cu<SUB>2</SUB>O nanoshell for SERS study. </LI> <LI> SERS contribution enables us to understand the possible enhancement of hybrid nanostructures. </LI> <LI> LSPR-induced carrier movement in Au@Cu<SUB>2</SUB>O nanocomposites. </LI> </UL> </P> <P><B>Graphical Abstract</B></P> <P>We designed the shell-dependent Au@Cu<SUB>2</SUB>O core-shell nanoparticles (NPs) for SERS study. For the electron-hole pairs in the Cu<SUB>2</SUB>O, the plasmon induced resonant energy transfer from Au to the Cu<SUB>2</SUB>O and the direct electron transfer simultaneously which can be observed from the SERS intensity.</P> <P>[DISPLAY OMISSION]</P>

Efficient End-to-End Failure Probing Matrix Construction in Data Center Networks

Jia, Zequn,Liu, Qiang,He, Ying,Wu, Qianqian,Liu, Ren Ping,Sun, Yantao 한국통신학회 2023 Journal of communications and networks Vol.25 No.4

Data centers play an essential role in the functioningof modern society. However, failures are unavoidable in datacenter networks (DCN) and will lead to negative impact on allapplications. Therefore, researchers are interested in the rapiddetection and localization of failures in DCNs. In this paper, we present a theoretical model to analyze theend-to-end failure detection methods in data center networks. Our numerical results verify that the proposed theoretical modelis accurate. In addition, we propose an algorithm to constructprobing matrices based on an enhanced probing path selectionindicator. We also introduce deep reinforcement learning (DRL)method to solve the problem and propose a DRL-based probingmatrix construction algorithm. Our experimental results showthat both of the proposed algorithms for constructing probingmatrices achieve better performance in detection accuracy thanexisting methods. We discussed different scenarios that thealgorithms are applicable to that can improve detection accuracyor construction speed performance.