University of Electronic Science and Technology of China

About: University of Electronic Science and Technology of China is a education organization based out in Chengdu, China. It is known for research contribution in the topics: Computer science & Antenna (radio). The organization has 50594 authors who have published 58502 publications receiving 711188 citations. The organization is also known as: UESTC.

Automatic Brain Tumor Segmentation Based on Cascaded Convolutional Neural Networks With Uncertainty Estimation.

Abstract: Automatic segmentation of brain tumors from medical images is important for clinical assessment and treatment planning of brain tumors. Recent years have seen an increasing use of convolutional neural networks (CNNs) for this task, but most of them use either 2D networks with relatively low memory requirement while ignoring 3D context, or 3D networks exploiting 3D features while with large memory consumption. In addition, existing methods rarely provide uncertainty information associated with the segmentation result. We propose a cascade of CNNs to segment brain tumors with hierarchical subregions from multi-modal Magnetic Resonance images (MRI), and introduce a 2.5D network that is a trade-off between memory consumption, model complexity and receptive field. In addition, we employ test-time augmentation to achieve improved segmentation accuracy, which also provides voxel-wise and structure-wise uncertainty information of the segmentation result. Experiments with BraTS 2017 dataset showed that our cascaded framework with 2.5D CNNs was one of the top performing methods (second-rank) for the BraTS challenge. We also validated our method with BraTS 2018 dataset and found that test-time augmentation improves brain tumor segmentation accuracy and that the resulting uncertainty information can indicate potential mis-segmentations and help to improve segmentation accuracy.

Social Turing Tests: Crowdsourcing Sybil Detection

Abstract: As popular tools for spreading spam and malware, Sybils (or fake accounts) pose a serious threat to online communities such as Online Social Networks (OSNs). Today, sophisticated attackers are creating realistic Sybils that effectively befriend legitimate users, rendering most automated Sybil detection techniques ineffective. In this paper, we explore the feasibility of a crowdsourced Sybil detection system for OSNs. We conduct a large user study on the ability of humans to detect today’s Sybil accounts, using a large corpus of ground-truth Sybil accounts from the Facebook and Renren networks. We analyze detection accuracy by both “experts” and “turkers” under a variety of conditions, and find that while turkers vary significantly in their effectiveness, experts consistently produce near-optimal results. We use these results to drive the design of a multi-tier crowdsourcing Sybil detection system. Using our user study data, we show that this system is scalable, and can be highly effective either as a standalone system or as a complementary technique to current tools.

Coherent Integration for Maneuvering Target Detection Based on Radon-Lv’s Distribution

Abstract: This letter considers the coherent integration problem for a maneuvering target, involving range migration (RM) and Doppler frequency migration (DFM) within one coherent pulse interval. A new coherent integration method, known as Radon-Lv’s distribution (RLVD), is proposed. It can not only eliminate the RM effect via jointly searching in the target’s motion parameters space, but also remove the DFM and achieve the coherent integration via Lv’s distribution (LVD). Finally, several simulations are provided to demonstrate the effectiveness. The results show that for detection ability, the proposed method is superior to the moving target detection (MTD), Radon-Fourier transform (RFT), and Radon-fractional Fourier transform (RFRFT) under low signal-to-noise-ratio (SNR) environment.

Learning Binary Codes for Maximum Inner Product Search

Abstract: Binary coding or hashing techniques are recognized to accomplish efficient near neighbor search, and have thus attracted broad interests in the recent vision and learning studies. However, such studies have rarely been dedicated to Maximum Inner Product Search (MIPS), which plays a critical role in various vision applications. In this paper, we investigate learning binary codes to exclusively handle the MIPS problem. Inspired by the latest advance in asymmetric hashing schemes, we propose an asymmetric binary code learning framework based on inner product fitting. Specifically, two sets of coding functions are learned such that the inner products between their generated binary codes can reveal the inner products between original data vectors. We also propose an alternative simpler objective which maximizes the correlations between the inner products of the produced binary codes and raw data vectors. In both objectives, the binary codes and coding functions are simultaneously learned without continuous relaxations, which is the key to achieving high-quality binary codes. We evaluate the proposed method, dubbed Asymmetric Inner-product Binary Coding (AIBC), relying on the two objectives on several large-scale image datasets. Both of them are superior to the state-of-the-art binary coding and hashing methods in performing MIPS tasks.

Abnormal resting-state cerebellar–cerebral functional connectivity in treatment-resistant depression and treatment sensitive depression

Abstract: Background Previous studies have commonly shown that patients with treatment-resistant depression (TRD) and treatment-sensitive depression (TSD) demonstrate a different cerebellar activity. No study has yet explored resting-state cerebellar–cerebral functional connectivity (FC) in these two groups. Here, seed-based FC approach was employed to test the hypothesis that patients with TRD and TSD had a different cerebellar–cerebral FC. The identified FC might be used to differentiate TRD from TSD. Methods Twenty-three patients with TRD, 22 patients with TSD, and 19 healthy subjects (HS) matched with age, gender, and education level participated in the scans. Seed-based connectivity analyses were performed by using cerebellar seeds. Results Relative to HS, both patient groups showed significantly decreased cerebellar–cerebral FC with the prefrontal cortex (PFC) (superior, middle, and inferior frontal gyrus) and default mode network (DMN) [superior, middle, and inferior temporal gyrus, precuneus (PCu), and inferior parietal lobule (IPL)], and increased FC with visual recognition network (lingual gyrus, middle occipital gyrus, and fusiform) and parahippocampal gyrus. However, the TRD group exhibited a more decreased FC than the TSD group, mainly in connected regions within DMN [PCu, angular gyrus (AG) and IPL]. Further receiver operating characteristic curves (ROC) analyses showed that cerebellar-DMN couplings could be applied as markers to differentiate the two subtypes with relatively high sensitivity and specificity. Conclusions Both patient groups demonstrate similar pattern of abnormal cerebellar–cerebral FC. Decreased FC between the cerebellum and regions within DMN might be used to separate the two patient groups.