arXiv subjects

Hongwei Li

Publications and source records attributed to Hongwei Li.

134 records · Page 8Linked to original sources

arXiv2018

Differential Diagnosis for Pancreatic Cysts in CT Scans Using Densely-Connected Convolutional Networks

The lethal nature of pancreatic ductal adenocarcinoma (PDAC) calls for early differential diagnosis of pancreatic cysts, which are identified in up to 16% of normal subjects, and some of which may develop into PDAC. Previous computer-aided developments have achieved certain accuracy for classification on segmented cystic lesions in CT. However, pancreatic cysts have a large variation in size and shape, and the precise segmentation of them remains rather challenging, which restricts the computer-aided interpretation of CT images acquired for differential diagnosis. We propose a computer-aided framework for early differential diagnosis of pancreatic cysts without pre-segmenting the lesions using densely-connected convolutional networks (Dense-Net). The Dense-Net learns high-level features from whole abnormal pancreas and builds mappings between medical imaging appearance to different pathological types of pancreatic cysts. To enhance the clinical applicability, we integrate saliency maps in the framework to assist the physicians to understand the decision of the deep learning method. The test on a cohort of 206 patients with 4 pathologically confirmed subtypes of pancreatic cysts has achieved an overall accuracy of 72.8%, which is significantly higher than the baseline accuracy of 48.1%, which strongly supports the clinical potential of our developed method.

cs.CV↗

arXiv2018

Deep CNNs for HEp-2 Cells Classification : A Cross-specimen Analysis

Automatic classification of Human Epithelial Type-2 (HEp-2) cells staining patterns is an important and yet a challenging problem. Although both shallow and deep methods have been applied, the study of deep convolutional networks (CNNs) on this topic is shallow to date, thus failed to claim its top position for this problem. In this paper, we propose a novel study of using CNNs for HEp-2 cells classification focusing on cross-specimen analysis, a key evaluation for generalization. For the first time, our study reveals several key factors of using CNNs for HEp-2 cells classification. Our proposed system achieves state-of-the-art classification accuracy on public benchmark dataset. Comparative experiments on different training data reveals that adding different specimens,rather than increasing in numbers by affine transformations, helps to train a good deep model. This opens a new avenue for adopting deep CNNs to HEp-2 cells classification.

cs.CV↗

arXiv2016

Observation of reversible orbital angular momentum transfer based on photon-phonon coupling

Orbital angular momentum (OAM) has gained great interest due to its most attractive feature of high dimensionality, and several ground-breaking demonstrations in communication based on OAM multiplexing have been carried out. Accordingly, a rapid data-density growth from OAM multiplexing has posed a great challenge to the signal-processing layer. Meanwhile, in another area, optical signal-processing circuit based on photon-phonon conversion has received considerable attention and made rapid progress. Here, with an aim of finding the intersection between OAM multiplexing and photon-phonon conversion, we report on the observation of reversible OAM photon-phonon conversion. A specific OAM state can be flexibly and controllably interconverted between photonic and phononic domains via Brillouin photon-phonon coupling within the decay time of acoustic signal, in which OAM and spin angular momentum are independently conserved. Our result demonstrates the controllable OAM transfer between photons and phonons, shows the potential of using OAM multiplexing to extend the capacity of photon-phonon conversion based signal-processing scheme, and may trigger the development of OAM-multiplexed photon-phonon circuit.

physics.optics↗

arXiv2015

Parametric amplification of orbital angular momentum beams based on light-acoustic interaction

A high fidelity amplification of beams carrying orbital angular momentum (OAM) is very crucial for OAM multiplexing and other OAM-based applications. Here, we report the first study of stimulated Brillouin amplification (SBA) for OAM beams, the energy conversion efficiency of photon-phonon coupling and the phase structure of amplified signals are investigated in collinear and noncollinear frame systems, respectively. Our results demonstrate that the OAM signals can be efficiently amplified without obvious noise introduced, and the modes of output signal are independent of the pump modes or the geometrical frames. Meanwhile, an OAM state depending on the optical modes and the geometrical frames is loaded into phonons by coherent light-acoustic interaction, which reveals more fundamental significance and a great application potential in OAM-multiplexing.

physics.optics↗

arXiv2015

Cheaper and Better: Selecting Good Workers for Crowdsourcing

Crowdsourcing provides a popular paradigm for data collection at scale. We study the problem of selecting subsets of workers from a given worker pool to maximize the accuracy under a budget constraint. One natural question is whether we should hire as many workers as the budget allows, or restrict on a small number of top-quality workers. By theoretically analyzing the error rate of a typical setting in crowdsourcing, we frame the worker selection problem into a combinatorial optimization problem and propose an algorithm to solve it efficiently. Empirical results on both simulated and real-world datasets show that our algorithm is able to select a small number of high-quality workers, and performs as good as, sometimes even better than, the much larger crowds as the budget allows.

stat.ML↗

arXiv2014

Error Rate Bounds and Iterative Weighted Majority Voting for Crowdsourcing

Crowdsourcing has become an effective and popular tool for human-powered computation to label large datasets. Since the workers can be unreliable, it is common in crowdsourcing to assign multiple workers to one task, and to aggregate the labels in order to obtain results of high quality. In this paper, we provide finite-sample exponential bounds on the error rate (in probability and in expectation) of general aggregation rules under the Dawid-Skene crowdsourcing model. The bounds are derived for multi-class labeling, and can be used to analyze many aggregation methods, including majority voting, weighted majority voting and the oracle Maximum A Posteriori (MAP) rule. We show that the oracle MAP rule approximately optimizes our upper bound on the mean error rate of weighted majority voting in certain setting. We propose an iterative weighted majority voting (IWMV) method that optimizes the error rate bound and approximates the oracle MAP rule. Its one step version has a provable theoretical guarantee on the error rate. The IWMV method is intuitive and computationally simple. Experimental results on simulated and real data show that IWMV performs at least on par with the state-of-the-art methods, and it has a much lower computational cost (around one hundred times faster) than the state-of-the-art methods.

stat.ML↗

arXiv2013

Error Rate Bounds in Crowdsourcing Models

Crowdsourcing is an effective tool for human-powered computation on many tasks challenging for computers. In this paper, we provide finite-sample exponential bounds on the error rate (in probability and in expectation) of hyperplane binary labeling rules under the Dawid-Skene crowdsourcing model. The bounds can be applied to analyze many common prediction methods, including the majority voting and weighted majority voting. These bound results could be useful for controlling the error rate and designing better algorithms. We show that the oracle Maximum A Posterior (MAP) rule approximately optimizes our upper bound on the mean error rate for any hyperplane binary labeling rule, and propose a simple data-driven weighted majority voting (WMV) rule (called one-step WMV) that attempts to approximate the oracle MAP and has a provable theoretical guarantee on the error rate. Moreover, we use simulated and real data to demonstrate that the data-driven EM-MAP rule is a good approximation to the oracle MAP rule, and to demonstrate that the mean error rate of the data-driven EM-MAP rule is also bounded by the mean error rate bound of the oracle MAP rule with estimated parameters plugging into the bound.

stat.ML↗

arXiv2009

Field Experiment on a Robust Hierarchical Metropolitan Quantum Cryptography Network

A hierarchical metropolitan quantum cryptography network upon the inner-city commercial telecom fiber cables is reported in this paper. The seven-user network contains a four-node backbone net with one node acting as the subnet gateway, a two-user subnet and a single-fiber access link, which is realized by the Faraday-Michelson Interferometer set-ups. The techniques of the quantum router, optical switch and trusted relay are assembled here to guarantee the feasibility and expandability of the quantum cryptography network. Five nodes of the network are located in the government departments and the secure keys generated by the quantum key distribution network are utilized to encrypt the instant video, sound, text messages and confidential files transmitting between these bureaus. The whole implementation including the hierarchical quantum cryptographic communication network links and corresponding application software shows a big step toward the practical user-oriented network with high security level.

quant-ph↗