Searcharxiv⌕ Search

arXiv subjects

Ye Wu

Publications and source records attributed to Ye Wu.

54 records · Page 3Linked to original sources
arXiv2023

Can SAM Segment Polyps?

Recently, Meta AI Research releases a general Segment Anything Model (SAM), which has demonstrated promising performance in several segmentation tasks. As we know, polyp segmentation is a fundamental task in the medical imaging field, which plays a critical role in the diagnosis and cure of colorectal cancer. In particular, applying SAM to the polyp segmentation task is interesting. In this report, we evaluate the performance of SAM in segmenting polyps, in which SAM is under unprompted settings. We hope this report will provide insights to advance this polyp segmentation field and promote more interesting works in the future. This project is publicly at https://github.com/taozh2017/SAMPolyp.

cs.CV↗
arXiv2023

Brain Tissue Segmentation Across the Human Lifespan via Supervised Contrastive Learning

Automatic segmentation of brain MR images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is critical for tissue volumetric analysis and cortical surface reconstruction. Due to dramatic structural and appearance changes associated with developmental and aging processes, existing brain tissue segmentation methods are only viable for specific age groups. Consequently, methods developed for one age group may fail for another. In this paper, we make the first attempt to segment brain tissues across the entire human lifespan (0-100 years of age) using a unified deep learning model. To overcome the challenges related to structural variability underpinned by biological processes, intensity inhomogeneity, motion artifacts, scanner-induced differences, and acquisition protocols, we propose to use contrastive learning to improve the quality of feature representations in a latent space for effective lifespan tissue segmentation. We compared our approach with commonly used segmentation methods on a large-scale dataset of 2,464 MR images. Experimental results show that our model accurately segments brain tissues across the lifespan and outperforms existing methods.

eess.IV↗
arXiv2022

Residue-based Label Protection Mechanisms in Vertical Logistic Regression

Federated learning (FL) enables distributed participants to collaboratively learn a global model without revealing their private data to each other. Recently, vertical FL, where the participants hold the same set of samples but with different features, has received increased attention. This paper first presents one label inference attack method to investigate the potential privacy leakages of the vertical logistic regression model. Specifically, we discover that the attacker can utilize the residue variables, which are calculated by solving the system of linear equations constructed by local dataset and the received decrypted gradients, to infer the privately owned labels. To deal with this, we then propose three protection mechanisms, e.g., additive noise mechanism, multiplicative noise mechanism, and hybrid mechanism which leverages local differential privacy and homomorphic encryption techniques, to prevent the attack and improve the robustness of the vertical logistic regression. model. Experimental results show that both the additive noise mechanism and the multiplicative noise mechanism can achieve efficient label protection with only a slight drop in model testing accuracy, furthermore, the hybrid mechanism can achieve label protection without any testing accuracy degradation, which demonstrates the effectiveness and efficiency of our protection techniques

cs.LG↗
arXiv2021

Feasibility study of TPC detector at high luminosity $Z$ pole on the circular collider

With the development of the circular collider, it is necessary to make accurate physics experimental measurements of particle properties at higher luminosity $Z$ pole. Micro-pattern gaseous detectors (MPGDs), which contain Gaseous Electron Multiplier (GEM) and Micro-mesh gaseous structures (Micromegas), have excellent potential for development as the readout devices of the time projection chamber (TPC) tracker detector. To meet the updated physics requirements of the high luminosity $Z$ from the preliminary concept design report (preCDR) to concept design report (CDR) at the circular electron positron collider (CEPC), In this paper, the space charge distortion of the TPC detector is simulated with the CEPC beam structure. Using the multi-physics simulation software package, the distribution of ion estimated by Geant4 is used as the input for the differential equation, and the relationship between the ion density distribution and electric field in the detector chamber is simulated. These simulation results show that the maximum deviation for Higgs $\mathcal{O}$(25 $μ$m) meets the performance requirements in CEPC TPC detector at the high luminosity $Z$ pole, while it is still a considerable challenge for $Z$ pole, with the maximum deviation $\mathcal{O}$($>100~μ$m). According to the previous developments, the cascaded structure of GEM and Micromegas detector has been measured. The new considerations of the detector's requirements were given, the gain needs to be reached to about 2000 with IBF$\times$Gain under 0.1, and IBF means the ions back flow ratio of the detector. The pixel TPC is a potential option to replace the traditional MPGDs with the low gain, low occupancy, and outstanding pattern recognition. Finally, some update parameters and experiments results were compared.

physics.ins-det↗
arXiv2021

HiVision: Rapid Visualization of Large-Scale Spatial Vector Data

Rapid visualization of large-scale spatial vector data is a long-standing challenge in Geographic Information Science. In existing methods, the computation overheads grow rapidly with data volumes, leading to the incapability of providing real-time visualization for large-scale spatial vector data, even with parallel acceleration technologies. To fill the gap, we present HiVision, a display-driven visualization model for large-scale spatial vector data. Different from traditional data-driven methods, the computing units in HiVision are pixels rather than spatial objects to achieve real-time performance, and efficient spatial-index-based strategies are introduced to estimate the topological relationships between pixels and spatial objects. HiVision can maintain exceedingly good performance regardless of the data volume due to the stable pixel number for display. In addition, an optimized parallel computing architecture is proposed in HiVision to ensure the ability of real-time visualization. Experiments show that our approach outperforms traditional methods in rendering speed and visual effects while dealing with large-scale spatial vector data, and can provide interactive visualization of datasets with billion-scale points/segments/edges in real-time with flexible rendering styles. The HiVision code is open-sourced at https://github.com/MemoryMmy/HiVision with an online demonstration.

cs.GR↗
arXiv2020

Probing Tissue Microarchitecture of the Baby Brain via Spherical Mean Spectrum Imaging

During the first years of life, the human brain undergoes dynamic spatially-heterogeneous changes, involving differentiation of neuronal types, dendritic arborization, axonal ingrowth, outgrowth and retraction, synaptogenesis, and myelination. To better quantify these changes, this article presents a method for probing tissue microarchitecture by characterizing water diffusion in a spectrum of length scales, factoring out the effects of intra-voxel orientation heterogeneity. Our method is based on the spherical means of the diffusion signal, computed over gradient directions for a fixed set of diffusion weightings (i.e., b-values). We decompose the spherical mean series at each voxel into a spherical mean spectrum (SMS), which essentially encodes the fractions of spin packets undergoing fine- to coarse-scale diffusion processes, characterizing hindered and restricted diffusion stemming respectively from extra- and intra-neurite water compartments. From the SMS, multiple orientation distribution invariant indices can be computed, allowing for example the quantification of neurite density, microscopic fractional anisotropy ($μ$FA), per-axon axial/radial diffusivity, and free/restricted isotropic diffusivity. We show maps of these indices for baby brains, demonstrating that microscopic tissue features can be extracted from the developing brain for greater sensitivity and specificity to development related changes. Also, we demonstrate that our method, called spherical mean spectrum imaging (SMSI), is fast, accurate, and can overcome the biases associated with other state-of-the-art microstructure models.

physics.med-ph↗
arXiv2020

Multifold Acceleration of Diffusion MRI via Slice-Interleaved Diffusion Encoding (SIDE)

Diffusion MRI (dMRI) is a unique imaging technique for in vivo characterization of tissue microstructure and white matter pathways. However, its relatively long acquisition time implies greater motion artifacts when imaging, for example, infants and Parkinson's disease patients. To accelerate dMRI acquisition, we propose in this paper (i) a diffusion encoding scheme, called Slice-Interleaved Diffusion Encoding (SIDE), that interleaves each diffusion-weighted (DW) image volume with slices that are encoded with different diffusion gradients, essentially allowing the slice-undersampling of image volume associated with each diffusion gradient to significantly reduce acquisition time, and (ii) a method based on deep learning for effective reconstruction of DW images from the highly slice-undersampled data. Evaluation based on the Human Connectome Project (HCP) dataset indicates that our method can achieve a high acceleration factor of up to 6 with minimal information loss. Evaluation using dMRI data acquired with SIDE acquisition demonstrates that it is possible to accelerate the acquisition by as much as 50 folds when combined with multi-band imaging.

physics.med-ph↗
arXiv2019

DeepBundle: Fiber Bundle Parcellation with Graph Convolution Neural Networks

Parcellation of whole-brain tractography streamlines is an important step for tract-based analysis of brain white matter microstructure. Existing fiber parcellation approaches rely on accurate registration between an atlas and the tractograms of an individual, however, due to large individual differences, accurate registration is hard to guarantee in practice. To resolve this issue, we propose a novel deep learning method, called DeepBundle, for registration-free fiber parcellation. Our method utilizes graph convolution neural networks (GCNNs) to predict the parcellation label of each fiber tract. GCNNs are capable of extracting the geometric features of each fiber tract and harnessing the resulting features for accurate fiber parcellation and ultimately avoiding the use of atlases and any registration method. We evaluate DeepBundle using data from the Human Connectome Project. Experimental results demonstrate the advantages of DeepBundle and suggest that the geometric features extracted from each fiber tract can be used to effectively parcellate the fiber tracts.

eess.IV↗
arXiv2019

Mitigating Gyral Bias in Cortical Tractography via Asymmetric Fiber Orientation Distributions

Diffusion tractography in brain connectomics often involves tracing axonal trajectories across gray-white matter boundaries in gyral blades of complex cortical convolutions. To date, gyral bias is observed in most tractography algorithms with streamlines predominantly terminating at gyral crowns instead of sulcal banks. This work demonstrates that asymmetric fiber orientation distribution functions (AFODFs), computed via a multi-tissue global estimation framework, can mitigate the effects of gyral bias, enabling fiber streamlines at gyral blades to make sharper turns into the cortical gray matter. We use ex-vivo data of an adult rhesus macaque and in-vivo data from the Human Connectome Project (HCP) to show that the fiber streamlines given by AFODFs bend more naturally into the cortex than the conventional symmetric FODFs in typical gyral blades. We demonstrate that AFODF tractography improves cortico-cortical connectivity and provides highly consistent outcomes between two different field strengths (3T and 7T).

q-bio.NC↗
arXiv2018

Web-Scale Responsive Visual Search at Bing

In this paper, we introduce a web-scale general visual search system deployed in Microsoft Bing. The system accommodates tens of billions of images in the index, with thousands of features for each image, and can respond in less than 200 ms. In order to overcome the challenges in relevance, latency, and scalability in such large scale of data, we employ a cascaded learning-to-rank framework based on various latest deep learning visual features, and deploy in a distributed heterogeneous computing platform. Quantitative and qualitative experiments show that our system is able to support various applications on Bing website and apps.

cs.CV↗
arXiv2017

Remote Channel Inference for Beamforming in Ultra-Dense Hyper-Cellular Network

In this paper, we propose a learning-based low-overhead channel estimation method for coordinated beamforming in ultra-dense networks. We first show through simulation that the channel state information (CSI) of geographically separated base stations (BSs) exhibits strong non-linear correlations in terms of mutual information. This finding enables us to adopt a novel learning-based approach to remotely infer the quality of different beamforming patterns at a dense-layer BS based on the CSI of an umbrella control-layer BS. The proposed scheme can reduce channel acquisition overhead by replacing pilot-aided channel estimation with the online inference from an artificial neural network, which is fitted offline. Moreover, we propose to exploit joint learning of multiple CBSs and involve more candidate beam patterns to obtain better performance. Simulation results based on stochastic ray-tracing channel models show that the proposed scheme can reach an accuracy of 99.74% in settings with 20 beamforming patterns.

cs.IT↗
arXiv2016

Magnetic Field Tunable Capacitive Dielectric:Ionic-liquid Sandwich Composites

We examined the tunability of the capacitance for GaFeO3-ionic liquid-GaFeO3 composite material by external magnetic and electric field. Up to 1.6 folds of capacitance tunability could be achieved at 957kHz with voltage 4v and magnetic field 0.02T applied. We show that the capacitance enhancement is due to the polarization coupling between dielectric layer and ionic liquid layer.

cond-mat.mtrl-sci↗
arXiv2015

Giant magnetic pumping of photovoltage and photocurrent using dielectric lossy material

The enhancement of photovoltage and photocurrent of material is fundamentally significant owing to the many interesting phenomena found and the potential applications. However, vast altering of magnitude-orders of photoelectricity has been technologically challenging. Here we report two dielectric materials Li2ZnSiO4 and Li2SiO3 showing high photovoltage and photocurrent tunability. When magnetic field increasing from 0.00015T up to 0.44T,it is found that 3850% of photovoltage tunability and 3841 % of photocurrent tunability in Li2ZnSiO4 , and 132.8% of photovoltage tunability and 132.5% of photocurrent tunability in Li2SiO3. A simple model that considers the effects of spin mixing/interaction and magnetically-tunable charge gradient is used to explain this interaction between magnetic field and the photoelectricity. This result indicates a magnetic approach can be potentially used for energy efficiency.

cond-mat.mtrl-sci↗
arXiv2015

Three possible mechanisms of capacitance enhancement under magnetic field: charge density gradient modulation, electron gas excitation and oscillatory magnetization- polarization coupling

Three mechanisms of capacitance enhance-ment by a magnetic field have been analyz-ed. Through semiclassical description of charge movement under a magnetic field, it can be shown that the charge density gradient, a term coupled with magnetic field strength, could be used to augment the magnetocapacitance. Also a magnetic field could enhance capacitance on the polarized metallic material surface due to the electron gas excitation. Finally, a magnetic field could produce oscillation in the capacitance when relating the polarization with the magnetization through the modification of standard free energy model. By deriving these three mechanisms, it can be seen that three approaches are of potential for exploring tunable dielectric materials.

cond-mat.mtrl-sci↗
arXiv2015

Impacts of suppressing guide on information spreading

It is quite common that guides are introduced to suppress the information spreading in modern society for different purposes. In this paper, an agent-based model is established to quantitatively analyze the impacts of suppressing guides on information spreading. We find that the spreading threshold depends on the attractiveness of the information and the topology of the social network with no suppressing guides at all. Usually, one would expect that the existence of suppressing guides in the spreading procedure may result in less diffusion of information within the overall network. However, we find that sometimes the opposite is true: the manipulating nodes of suppressing guides may lead to more extensive information spreading when there are audiences with the reversal mind. These results can provide valuable theoretical references to public opinion guidance on various information, e.g., rumor or news spreading.

physics.soc-ph↗
arXiv2012

Pairwise interaction pattern in the weighted communication network

Although recent studies show that both topological structures and human dynamics can strongly affect information spreading on social networks, the complicated interplay of the two significant factors has not yet been clearly described. In this work, we find a strong pairwise interaction based on analyzing the weighted network generated by the short message communication dataset within a Chinese tele-communication provider. The pairwise interaction bridges the network topological structure and human interaction dynamics, which can promote local information spreading between pairs of communication partners and in contrast can also suppress global information (e.g., rumor) cascade and spreading. In addition, the pairwise interaction is the basic pattern of group conversations and it can greatly reduce the waiting time of communication events between a pair of intimate friends. Our findings are also helpful for communication operators to design novel tariff strategies and optimize their communication services.

physics.soc-ph↗
arXiv2011

Effects of gradient coupling on amplitude death in nonidentical oscillators

In this work, we investigate gradient coupling effect on amplitude death in an array of N cou- pled nonidentical oscillators with no-flux boundary conditions and periodic boundary conditions respectively. We find that the effects of gradient coupling on amplitude death in diffusive coupled nonidentical oscillators is quite different between those two boundaries conditions. With no-flux boundary conditions, there is a system size related critical gradient coupling $r_c$ within which the gradient coupling tends to monotonically enlarge the amplitude death domain in the parameter space. With the periodical boundary conditions, there is an optimal gradient coupling constant $r_o$ to realize largest AD domain. The gradient coupling first enlarges then decreases the amplitude death domain of diffusive coupled oscillators. The amplitude death domain of parameter space are analytically predicted for small number of gradient coupled oscillators.

nlin.CD↗