arXiv subjects

Wei Zhao

Publications and source records attributed to Wei Zhao.

At least 325 records · Page 18Linked to original sources

arXiv2020

Dual-energy Computed Tomography Imaging from Contrast-enhanced Single-energy Computed Tomography

In a standard computed tomography (CT) image, pixels having the same Hounsfield Units (HU) can correspond to different materials and it is therefore challenging to differentiate and quantify materials. Dual-energy CT (DECT) is desirable to differentiate multiple materials, but DECT scanners are not widely available as single-energy CT (SECT) scanners. Here we purpose a deep learning approach to perform DECT imaging by using standard SECT data. We designed a predenoising and difference learning mechanism to generate DECT images from SECT data. The performance of the deep learning-based DECT approach was studied using images from patients who received contrast-enhanced abdomen DECT scan with a popular DE application: virtual non-contrast (VNC) imaging and contrast quantification. Clinically relevant metrics were used for quantitative assessment. The absolute HU difference between the predicted and original high-energy CT images are 1.3 HU, 1.6 HU, 1.8 HU and 1.3 HU for the ROIs on aorta, liver, spine and stomach, respectively. The aorta iodine quantification difference between iodine maps obtained from the original and deep learning DECT images is smaller than 1.0\%, and the noise levels in the material images have been reduced by more than 7-folds for the latter. This study demonstrates that highly accurate DECT imaging with single low-energy data is achievable by using a deep learning approach. The proposed method allows us to obtain high-quality DECT images without paying the overhead of conventional hardware-based DECT solutions and thus leads to a new paradigm of spectral CT imaging.

physics.med-ph↗

arXiv2020

Active Testing: An Unbiased Evaluation Method for Distantly Supervised Relation Extraction

Distant supervision has been a widely used method for neural relation extraction for its convenience of automatically labeling datasets. However, existing works on distantly supervised relation extraction suffer from the low quality of test set, which leads to considerable biased performance evaluation. These biases not only result in unfair evaluations but also mislead the optimization of neural relation extraction. To mitigate this problem, we propose a novel evaluation method named active testing through utilizing both the noisy test set and a few manual annotations. Experiments on a widely used benchmark show that our proposed approach can yield approximately unbiased evaluations for distantly supervised relation extractors.

cs.CL↗

arXiv2020

Ape210K: A Large-Scale and Template-Rich Dataset of Math Word Problems

Automatic math word problem solving has attracted growing attention in recent years. The evaluation datasets used by previous works have serious limitations in terms of scale and diversity. In this paper, we release a new large-scale and template-rich math word problem dataset named Ape210K. It consists of 210K Chinese elementary school-level math problems, which is 9 times the size of the largest public dataset Math23K. Each problem contains both the gold answer and the equations needed to derive the answer. Ape210K is also of greater diversity with 56K templates, which is 25 times more than Math23K. Our analysis shows that solving Ape210K requires not only natural language understanding but also commonsense knowledge. We expect Ape210K to be a benchmark for math word problem solving systems. Experiments indicate that state-of-the-art models on the Math23K dataset perform poorly on Ape210K. We propose a copy-augmented and feature-enriched sequence to sequence (seq2seq) model, which outperforms existing models by 3.2% on the Math23K dataset and serves as a strong baseline of the Ape210K dataset. The gap is still significant between human and our baseline model, calling for further research efforts. We make Ape210K dataset publicly available at https://github.com/yuantiku/ape210k

cs.CL↗

arXiv2020

Beam data modeling of linear accelerators (linacs) through machine learning and its potential applications in fast and robust linac commissioning and quality assurance

Background and purpose: To propose a novel machine learning-based method for reliable and accurate modeling of linac beam data applicable to the processes of linac commissioning and QA. Materials and methods: We hypothesize that the beam data is a function of inherent linac features and percentage depth doses (PDDs) and profiles of different field sizes are correlated with each other. The correlation is formulated as a multivariable regression problem using a machine learning framework. Varian TrueBeam beam data sets (n=43) acquired from multiple institutions were used to evaluate the framework. The data sets included PDDs and profiles across different energies and field sizes. A multivariate regression model was trained for prediction of beam specific PDDs and profiles of different field sizes using a 10x10cm$^2$ field as input. Results: Predictions of PDDs were achieved with a mean absolute percent relative error (%RE) of 0.19-0.35% across the different beam energies investigated. The maximum mean absolute %RE was 0.93%. For profile prediction, the mean absolute %RE was 0.66-0.93% with a maximum absolute %RE of 3.76%. The largest uncertainties in the PDD and profile predictions were found at the build-up region and at the field penumbra, respectively. The prediction accuracy increased with the number of training sets up to around 20 training sets. Conclusions: Through this novel machine learning-based method we have shown accurate and reproducible generation of beam data for linac commissioning for routine radiation therapy. This method has the potential to simplify the linac commissioning procedure, save time and manpower while increasing the accuracy of the commissioning process.

physics.med-ph↗

arXiv2020

Bayesian Hierarchical Models for High-Dimensional Mediation Analysis with Coordinated Selection of Correlated Mediators

We consider Bayesian high-dimensional mediation analysis to identify among a large set of correlated potential mediators the active ones that mediate the effect from an exposure variable to an outcome of interest. Correlations among mediators are commonly observed in modern data analysis; examples include the activated voxels within connected regions in brain image data, regulatory signals driven by gene networks in genome data and correlated exposure data from the same source. When correlations are present among active mediators, mediation analysis that fails to account for such correlation can be sub-optimal and may lead to a loss of power in identifying active mediators. Building upon a recent high-dimensional mediation analysis framework, we propose two Bayesian hierarchical models, one with a Gaussian mixture prior that enables correlated mediator selection and the other with a Potts mixture prior that accounts for the correlation among active mediators in mediation analysis. We develop efficient sampling algorithms for both methods. Various simulations demonstrate that our methods enable effective identification of correlated active mediators, which could be missed by using existing methods that assume prior independence among active mediators. The proposed methods are applied to the LIFECODES birth cohort and the Multi-Ethnic Study of Atherosclerosis (MESA) and identified new active mediators with important biological implications.

stat.AP↗

arXiv2020

Bayesian Sparse Mediation Analysis with Targeted Penalization of Natural Indirect Effects

Causal mediation analysis aims to characterize an exposure's effect on an outcome and quantify the indirect effect that acts through a given mediator or a group of mediators of interest. With the increasing availability of measurements on a large number of potential mediators, like the epigenome or the microbiome, new statistical methods are needed to simultaneously accommodate high-dimensional mediators while directly target penalization of the natural indirect effect (NIE) for active mediator identification. Here, we develop two novel prior models for identification of active mediators in high-dimensional mediation analysis through penalizing NIEs in a Bayesian paradigm. Both methods specify a joint prior distribution on the exposure-mediator effect and mediator-outcome effect with either (a) a four-component Gaussian mixture prior or (b) a product threshold Gaussian prior. By jointly modeling the two parameters that contribute to the NIE, the proposed methods enable penalization on their product in a targeted way. Resultant inference can take into account the four-component composite structure underlying the NIE. We show through simulations that the proposed methods improve both selection and estimation accuracy compared to other competing methods. We applied our methods for an in-depth analysis of two ongoing epidemiologic studies: the Multi-Ethnic Study of Atherosclerosis (MESA) and the LIFECODES birth cohort. The identified active mediators in both studies reveal important biological pathways for understanding disease mechanisms.

stat.AP↗

arXiv2020

On Manually Reverse Engineering Communication Protocols of Linux Based IoT Systems

IoT security and privacy has raised grave concerns. Efforts have been made to design tools to identify and understand vulnerabilities of IoT systems. Most of the existing protocol security analysis techniques rely on a well understanding of the underlying communication protocols. In this paper, we systematically present the first manual reverse engineering framework for discovering communication protocols of embedded Linux based IoT systems. We have successfully applied our framework to reverse engineer a number of IoT systems. As an example, we present a detailed use of the framework reverse-engineering the WeMo smart plug communication protocol by extracting the firmware from the flash, performing static and dynamic analysis of the firmware and analyzing network traffic. The discovered protocol exposes severe design flaws that allow attackers to control or deny the service of victim plugs. Our manual reverse engineering framework is generic and can be applied to both read-only and writable Embedded Linux filesystems.

cs.CR↗

arXiv2020

Sapphire: Automatic Configuration Recommendation for Distributed Storage Systems

Modern distributed storage systems come with aplethora of configurable parameters that controlmodule behavior and affect system performance. Default settings provided by developers are often suboptimal for specific user cases. Tuning parameters can provide significant performance gains but is a difficult task requiring profound experience and expertise, due to the immense number of configurable parameters, complex inner dependencies and non-linearsystem behaviors. To overcome these difficulties, we propose an automatic simulation-based approach, Sapphire, to recommend optimal configurations by leveraging machine learning and black-box optimization techniques. We evaluate Sapphire on Ceph. Results show that Sapphire significantly boosts Ceph performance to 2.2x compared to the default configuration.

cs.DC↗

arXiv2020

From $μ_0$ to $e$: A Survey of Major Impacts for Electrical Measurements in Recent SI Revision

A milestone revision of the International System of Units (SI) was made at the 26th General Conference on Weights and Measures that four of the seven SI base units, i.e. kilogram, ampere, kelvin, and mole, are redefined by fundamental physical constants of nature. The SI base unit founding the electrical measurement activities, i.e. ampere, is defined by fixing the numerical value of the elementary charge to $e=1.602\,176\,634\times10^{-19}$C. For electrical measurement, several major adjustments, mostly positive, are involved in this SI revision. In this paper, the main impacts of the new SI for electrical measurement activities are surveyed under the new framework.

physics.ins-det↗

arXiv2020

On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation

Evaluation of cross-lingual encoders is usually performed either via zero-shot cross-lingual transfer in supervised downstream tasks or via unsupervised cross-lingual textual similarity. In this paper, we concern ourselves with reference-free machine translation (MT) evaluation where we directly compare source texts to (sometimes low-quality) system translations, which represents a natural adversarial setup for multilingual encoders. Reference-free evaluation holds the promise of web-scale comparison of MT systems. We systematically investigate a range of metrics based on state-of-the-art cross-lingual semantic representations obtained with pretrained M-BERT and LASER. We find that they perform poorly as semantic encoders for reference-free MT evaluation and identify their two key limitations, namely, (a) a semantic mismatch between representations of mutual translations and, more prominently, (b) the inability to punish "translationese", i.e., low-quality literal translations. We propose two partial remedies: (1) post-hoc re-alignment of the vector spaces and (2) coupling of semantic-similarity based metrics with target-side language modeling. In segment-level MT evaluation, our best metric surpasses reference-based BLEU by 5.7 correlation points.

cs.CL↗

arXiv2020

Dual-energy CT imaging from single-energy CT data with material decomposition convolutional neural network

Dual-energy computed tomography (DECT) is of great significance for clinical practice due to its huge potential to provide material-specific information. However, DECT scanners are usually more expensive than standard single-energy CT (SECT) scanners and thus are less accessible to undeveloped regions. In this paper, we show that the energy-domain correlation and anatomical consistency between standard DECT images can be harnessed by a deep learning model to provide high-performance DECT imaging from fully-sampled low-energy data together with single-view high-energy data, which can be obtained by using a scout-view high-energy image. We demonstrate the feasibility of the approach with contrast-enhanced DECT scans from 5,753 slices of images of twenty-two patients and show its superior performance on DECT applications. The deep learning-based approach could be useful to further significantly reduce the radiation dose of current premium DECT scanners and has the potential to simplify the hardware of DECT imaging systems and to enable DECT imaging using standard SECT scanners.

physics.med-ph↗

arXiv2020

Synergistic Learning of Lung Lobe Segmentation and Hierarchical Multi-Instance Classification for Automated Severity Assessment of COVID-19 in CT Images

Understanding chest CT imaging of the coronavirus disease 2019 (COVID-19) will help detect infections early and assess the disease progression. Especially, automated severity assessment of COVID-19 in CT images plays an essential role in identifying cases that are in great need of intensive clinical care. However, it is often challenging to accurately assess the severity of this disease in CT images, due to variable infection regions in the lungs, similar imaging biomarkers, and large inter-case variations. To this end, we propose a synergistic learning framework for automated severity assessment of COVID-19 in 3D CT images, by jointly performing lung lobe segmentation and multi-instance classification. Considering that only a few infection regions in a CT image are related to the severity assessment, we first represent each input image by a bag that contains a set of 2D image patches (with each cropped from a specific slice). A multi-task multi-instance deep network (called M$^2$UNet) is then developed to assess the severity of COVID-19 patients and also segment the lung lobe simultaneously. Our M$^2$UNet consists of a patch-level encoder, a segmentation sub-network for lung lobe segmentation, and a classification sub-network for severity assessment (with a unique hierarchical multi-instance learning strategy). Here, the context information provided by segmentation can be implicitly employed to improve the performance of severity assessment. Extensive experiments were performed on a real COVID-19 CT image dataset consisting of 666 chest CT images, with results suggesting the effectiveness of our proposed method compared to several state-of-the-art methods.

eess.IV↗

arXiv2020

A deep learning approach for virtual monochromatic spectral CT imaging with a standard single energy CT scanner

Purpose/Objectives: To develop and assess a strategy of using deep learning (DL) to generate virtual monochromatic CT (VMCT) images from a single-energy CT (SECT) scan. Materials/Methods: The proposed data-driven VMCT imaging consists of two steps: (i) using a supervised DL model trained with a large number of 100 kV and 140 kV dual-energy CT (DECT) image pairs to produce the corresponding high-energy CT image from a low-energy image; and (ii) reconstructing VMCT images with energy ranging from 40 to 150 keV. To evaluate the performance of the method, we retrospectively studied 6,767 abdominal DECT images. The VMCT images reconstructed using both DL-derived DECT (DL-DECT) images and the images from DECT scanner were compared quantitatively. Paired-sample t-tests were used for statistical analysis to show the consistency and precision of calculated HU values. Results: Excellent agreement was found between the DL-DECT and the ground truth DECT images (p values ranged from 0.50 to 0.95). Noise reduction up to 68% (from 163 HU to 51 HU) was achieved for DL-based VMCT imaging as compared to that obtained by using the standard DECT. For the DL-based VMCT, the maximum iodine contrast-to-noise ratio (CNR) for each patient (ranging from 15.1 to 16.6) was achieved at 40 keV. In addition to the enormous benefit of VMCT acquisition with merely a SECT image, an improvement of CNR as high as 55% (from 10.7 to 16.6) was attained with the proposed approach. Conclusions: This study demonstrates that high-quality VMCT images can be obtained with only a SECT scan.

physics.med-ph↗

arXiv2020

SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization

We study unsupervised multi-document summarization evaluation metrics, which require neither human-written reference summaries nor human annotations (e.g. preferences, ratings, etc.). We propose SUPERT, which rates the quality of a summary by measuring its semantic similarity with a pseudo reference summary, i.e. selected salient sentences from the source documents, using contextualized embeddings and soft token alignment techniques. Compared to the state-of-the-art unsupervised evaluation metrics, SUPERT correlates better with human ratings by 18-39%. Furthermore, we use SUPERT as rewards to guide a neural-based reinforcement learning summarizer, yielding favorable performance compared to the state-of-the-art unsupervised summarizers. All source code is available at https://github.com/yg211/acl20-ref-free-eval.

cs.CL↗

arXiv2020

Single-photon scattering and bound states in an atom-waveguide system with two or multiple coupling points

In this paper, we investigate the single-photon scattering and bound states in a one-dimensional coupled-resonator waveguide which couples to a single artificial giant atom with two or more coupling points. When the atom couples to the waveguide via two resonators, the single-photon reflection rate is characterized by either Breit-Wigner or Fano line shapes. When the atom couples to the waveguide via multiple resonators, we numerically show how the destructive interference effect leads to a complete single-photon reflection. We also find a phase transition phenomena for the multi-resonator coupling case, which reveals that the upper bound state only exists when the atom-waveguide coupling strength is above a critical value.

quant-ph↗

arXiv2020

COVID-19 Chest CT Image Segmentation -- A Deep Convolutional Neural Network Solution

A novel coronavirus disease 2019 (COVID-19) was detected and has spread rapidly across various countries around the world since the end of the year 2019, Computed Tomography (CT) images have been used as a crucial alternative to the time-consuming RT-PCR test. However, pure manual segmentation of CT images faces a serious challenge with the increase of suspected cases, resulting in urgent requirements for accurate and automatic segmentation of COVID-19 infections. Unfortunately, since the imaging characteristics of the COVID-19 infection are diverse and similar to the backgrounds, existing medical image segmentation methods cannot achieve satisfactory performance. In this work, we try to establish a new deep convolutional neural network tailored for segmenting the chest CT images with COVID-19 infections. We firstly maintain a large and new chest CT image dataset consisting of 165,667 annotated chest CT images from 861 patients with confirmed COVID-19. Inspired by the observation that the boundary of the infected lung can be enhanced by adjusting the global intensity, in the proposed deep CNN, we introduce a feature variation block which adaptively adjusts the global properties of the features for segmenting COVID-19 infection. The proposed FV block can enhance the capability of feature representation effectively and adaptively for diverse cases. We fuse features at different scales by proposing Progressive Atrous Spatial Pyramid Pooling to handle the sophisticated infection areas with diverse appearance and shapes. We conducted experiments on the data collected in China and Germany and show that the proposed deep CNN can produce impressive performance effectively.

eess.IV↗

arXiv2020

Quantum key distribution with dissipative Kerr soliton generated by on-chip microresonators

Quantum key distribution (QKD) can distribute symmetric key bits between remote legitimate users with the guarantee of quantum mechanics principles. For practical applications, the compact and robust photonic components for QKD are essential, and there are increasing attention to integrate the source, detector and modulators on a photonic chip. However, the massive and parallel QKD based on wavelength multiplexing are still challenge, due to the limited coherent light sources on the chip. Here, we introduce the Kerr dissipative soliton in a microresonator, which provides the locked coherent frequency comb with 49GHz frequency spacing, for QKD. We demonstrate the parallel QKD by demulplexing the coherent comb lines form the soliton, and showing the potential of Gbps secret key rate if the hundreds of channels covering C and L bands are fully exploited. The demonstrated soliton based QKD architecture are compatible with the efforts of quantum photonic integrated circuits, which are compact, robust and low-cost, and provides a competitive platform of practical QKD chip.

quant-ph↗

arXiv2020

Sharp uncertainty principles on general Finsler manifolds

The paper is devoted to sharp uncertainty principles (Heisenberg-Pauli-Weyl, Caffarelli-Kohn-Nirenberg and Hardy inequalities) on forward complete Finsler manifolds endowed with an arbitrary measure. Under mild assumptions, the existence of extremals corresponding to the sharp constants in the Heisenberg-Pauli-Weyl and Caffarelli-Kohn-Nirenberg inequalities fully characterizes the nature of the Finsler manifold in terms of three non-Riemannian quantities, namely, its reversibility and the vanishing of the flag curvature and $S$-curvature induced by the measure, respectively. It turns out in particular that the Busemann-Hausdorff measure is the optimal one in the study of sharp uncertainty principles on Finsler manifolds. The optimality of our results are supported by Randers-type Finslerian examples originating from the Zermelo navigation problem.

math.AP↗