arXiv subjects

Yan Liu

Publications and source records attributed to Yan Liu.

At least 361 records · Page 20Linked to original sources

arXiv2021

IDOL-Net: An Interactive Dual-Domain Parallel Network for CT Metal Artifact Reduction

Due to the presence of metallic implants, the imaging quality of computed tomography (CT) would be heavily degraded. With the rapid development of deep learning, several network models have been proposed for metal artifact reduction (MAR). Since the dual-domain MAR methods can leverage the hybrid information from both sinogram and image domains, they have significantly improved the performance compared to single-domain methods. However,current dual-domain methods usually operate on both domains in a specific order, which implicitly imposes a certain priority prior into MAR and may ignore the latent information interaction between both domains. To address this problem, in this paper, we propose a novel interactive dualdomain parallel network for CT MAR, dubbed as IDOLNet. Different from existing dual-domain methods, the proposed IDOL-Net is composed of two modules. The disentanglement module is utilized to generate high-quality prior sinogram and image as the complementary inputs. The follow-up refinement module consists of two parallel and interactive branches that simultaneously operate on image and sinogram domain, fully exploiting the latent information interaction between both domains. The simulated and clinical results demonstrate that the proposed IDOL-Net outperforms several state-of-the-art models in both qualitative and quantitative aspects.

physics.med-ph↗

arXiv2021

Adversarial Multiscale Feature Learning for Overlapping Chromosome Segmentation

Chromosome karyotype analysis is of great clinical importance in the diagnosis and treatment of diseases, especially for genetic diseases. Since manual analysis is highly time and effort consuming, computer-assisted automatic chromosome karyotype analysis based on images is routinely used to improve the efficiency and accuracy of the analysis. Due to the strip shape of the chromosomes, they easily get overlapped with each other when imaged, significantly affecting the accuracy of the analysis afterward. Conventional overlapping chromosome segmentation methods are usually based on manually tagged features, hence, the performance of which is easily affected by the quality, such as resolution and brightness, of the images. To address the problem, in this paper, we present an adversarial multiscale feature learning framework to improve the accuracy and adaptability of overlapping chromosome segmentation. Specifically, we first adopt the nested U-shape network with dense skip connections as the generator to explore the optimal representation of the chromosome images by exploiting multiscale features. Then we use the conditional generative adversarial network (cGAN) to generate images similar to the original ones, the training stability of which is enhanced by applying the least-square GAN objective. Finally, we employ Lovasz-Softmax to help the model converge in a continuous optimization setting. Comparing with the established algorithms, the performance of our framework is proven superior by using public datasets in eight evaluation criteria, showing its great potential in overlapping chromosome segmentation

cs.CV↗

arXiv2021

A General Deep Reinforcement Learning Framework for Grant-Free NOMA Optimization in mURLLC

Grant-free non-orthogonal multiple access (GF-NOMA) is a potential technique to support massive Ultra-Reliable and Low-Latency Communication (mURLLC) service. However, the dynamic resource configuration in GF-NOMA systems is challenging due to random traffics and collisions, that are unknown at the base station (BS). Meanwhile, joint consideration of the latency and reliability requirements makes the resource configuration of GF-NOMA for mURLLC more complex. To address this problem, we develop a general learning framework for signature-based GF-NOMA in mURLLC service taking into account the multiple access signature collision, the UE detection, as well as the data decoding procedures for the K-repetition GF and the Proactive GF schemes. The goal of our learning framework is to maximize the long-term average number of successfully served users (UEs) under the latency constraint. We first perform a real-time repetition value configuration based on a double deep Q-Network (DDQN) and then propose a Cooperative Multi-Agent learning technique based on the DQN (CMA-DQN) to optimize the configuration of both the repetition values and the contention-transmission unit (CTU) numbers. Our results show that the number of successfully served UEs under the same latency constraint in our proposed learning framework is up to ten times for the K-repetition scheme, and two times for the Proactive scheme, more than that with fixed repetition values and CTU numbers. In addition, the superior performance of CMA-DQN over the conventional load estimation-based approach (LE-URC) demonstrates its capability in dynamically configuring in long term. Importantly, our general learning framework can be used to optimize the resource configuration problems in all the signature-based GF-NOMA schemes.

cs.IT↗

arXiv2021

Muon reconstruction with a convolutional neural network in the JUNO detector

The Jiangmen Underground Neutrino Observatory (JUNO) is designed to determine the neutrino mass ordering and measure neutrino oscillation parameters. A precise muon reconstruction is crucial to reduce one of the major backgrounds induced by cosmic muons. This article proposes a novel muon reconstruction method based on convolutional neural network (CNN) models. In this method, the track information reconstructed by the top tracker is used for network training. The training dataset is augmented by applying a rotation to muon tracks to compensate for the limited angular coverage of the top tracker. The muon reconstruction with the CNN model can produce unbiased tracks with performance that spatial resolution is better than 10 cm and angular resolution is better than 0.6 degrees. By using a GPU accelerated implementation a speedup factor of 100 compared to existing CPU techniques has been demonstrated.

physics.ins-det↗

arXiv2021

Star-critical Gallai-Ramsey numbers of graphs

The Gallai-Ramsey number $gr_{k}(K_{3}: H_{1}, H_{2}, \cdots, H_{k})$ is the smallest integer $n$ such that every $k$-edge-colored $K_{n}$ contains either a rainbow $K_3$ or a monochromatic $H_{i}$ in color $i$ for some $i\in [k]$. We find the largest star that can be removed from $K_n$ such that the underlying graph is still forced to have a rainbow $K_3$ or a monochromatic $H_{i}$ in color $i$ for some $i\in [k]$. Thus, we define the star-critical Gallai-Ramsey number $gr_{k}^{*}(K_3: H_{1}, H_{2}, \cdots, H_{k})$ as the smallest integer $s$ such that every $k$-edge-colored $K_{n}-K_{1, n-1-s}$ contains either a rainbow $K_3$ or a monochromatic $H_{i}$ in color $i$ for some $i\in [k]$. When $H=H_{1}=\cdots=H_{k}$, we simply denote $gr_{k}^{*}(K_{3}: H_{1}, H_{2}, \cdots, H_{k})$ by $gr_{k}^{*}(K_{3}: H)$. We determine the star-critical Gallai-Ramsey numbers for complete graphs and some small graphs. Furthermore, we show that $gr_{k}^{*}(K_3: H)$ is exponential in $k$ if $H$ is not bipartite, linear in $k$ if $H$ is bipartite but not a star and constant (not depending on $k$) if $H$ is a star.

math.CO↗

arXiv2021

Interpretable Artificial Intelligence through the Lens of Feature Interaction

Interpretation of deep learning models is a very challenging problem because of their large number of parameters, complex connections between nodes, and unintelligible feature representations. Despite this, many view interpretability as a key solution to trustworthiness, fairness, and safety, especially as deep learning is applied to more critical decision tasks like credit approval, job screening, and recidivism prediction. There is an abundance of good research providing interpretability to deep learning models; however, many of the commonly used methods do not consider a phenomenon called "feature interaction." This work first explains the historical and modern importance of feature interactions and then surveys the modern interpretability methods which do explicitly consider feature interactions. This survey aims to bring to light the importance of feature interactions in the larger context of machine learning interpretability, especially in a modern context where deep learning models heavily rely on feature interactions.

cs.LG↗

arXiv2021

Topological modes in relativistic hydrodynamics

We show that gapless modes in relativistic hydrodynamics could become topologically nontrivial by weakly breaking the conservation of energy momentum tensor in a specific way. This system has topological semimetal-like crossing nodes in the spectrum of hydrodynamic modes that require the protection of a special combination of translational and boost symmetries in two spatial directions. We confirm the nontrivial topology from the existence of an undetermined Berry phase. These energy momentum non-conservation terms could naturally be produced by an external gravitational field that comes from a reference frame change from the original inertial frame, i.e. by fictitious forces in a non-inertial reference frame. This non-inertial frame is the rest frame of an accelerating observer moving along a trajectory of a helix. This suggests that topologically trivial modes could become nontrivial by being observed in a special non-inertial reference frame, and this fact could be verified in laboratories, in principle. Finally, we propose a holographic realization of this system.

hep-th↗

arXiv2021

DAN-Net: Dual-Domain Adaptive-Scaling Non-local Network for CT Metal Artifact Reduction

Metal implants can heavily attenuate X-rays in computed tomography (CT) scans, leading to severe artifacts in reconstructed images, which significantly jeopardize image quality and negatively impact subsequent diagnoses and treatment planning. With the rapid development of deep learning in the field of medical imaging, several network models have been proposed for metal artifact reduction (MAR) in CT. Despite the encouraging results achieved by these methods, there is still much room to further improve performance. In this paper, a novel Dual-domain Adaptive-scaling Non-local network (DAN-Net) for MAR. We correct the corrupted sinogram using adaptive scaling first to preserve more tissue and bone details as a more informative input. Then, an end-to-end dual-domain network is adopted to successively process the sinogram and its corresponding reconstructed image generated by the analytical reconstruction layer. In addition, to better suppress the existing artifacts and restrain the potential secondary artifacts caused by inaccurate results of the sinogram-domain network, a novel residual sinogram learning strategy and nonlocal module are leveraged in the proposed network model. In the experiments, the proposed DAN-Net demonstrates performance competitive with several state-of-the-art MAR methods in both qualitative and quantitative aspects.

physics.med-ph↗

arXiv2021

MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Dataset

The recent release of large-scale healthcare datasets has greatly propelled the research of data-driven deep learning models for healthcare applications. However, due to the nature of such deep black-boxed models, concerns about interpretability, fairness, and biases in healthcare scenarios where human lives are at stake call for a careful and thorough examinations of both datasets and models. In this work, we focus on MIMIC-IV (Medical Information Mart for Intensive Care, version IV), the largest publicly available healthcare dataset, and conduct comprehensive analyses of dataset representation bias as well as interpretability and prediction fairness of deep learning models for in-hospital mortality prediction. In terms of interpretabilty, we observe that (1) the best performing interpretability method successfully identifies critical features for mortality prediction on various prediction models; (2) demographic features are important for prediction. In terms of fairness, we observe that (1) there exists disparate treatment in prescribing mechanical ventilation among patient groups across ethnicity, gender and age; (2) all of the studied mortality predictors are generally fair while the IMV-LSTM (Interpretable Multi-Variable Long Short-Term Memory) model provides the most accurate and unbiased predictions across all protected groups. We further draw concrete connections between interpretability methods and fairness metrics by showing how feature importance from interpretability methods can be beneficial in quantifying potential disparities in mortality predictors.

cs.LG↗

arXiv2021

Modeling Treatment Effect Modification in Multidrug-Resistant Tuberculosis in an Individual Patient Data Meta-Analysis

Effect modification occurs while the effect of the treatment is not homogeneous across the different strata of patient characteristics. When the effect of treatment may vary from individual to individual, precision medicine can be improved by identifying patient covariates to estimate the size and direction of the effect at the individual level. However, this task is statistically challenging and typically requires large amounts of data. Investigators may be interested in using the individual patient data (IPD) from multiple studies to estimate these treatment effect models. Our data arise from a systematic review of observational studies contrasting different treatments for multidrug-resistant tuberculosis (MDR-TB), where multiple antimicrobial agents are taken concurrently to cure the infection. We propose a marginal structural model (MSM) for effect modification by different patient characteristics and co-medications in a meta-analysis of observational IPD. We develop, evaluate, and apply a targeted maximum likelihood estimator (TMLE) for the doubly robust estimation of the parameters of the proposed MSM in this context. In particular, we allow for differential availability of treatments across studies, measured confounding within and across studies, and random effects by study.

stat.ME↗

arXiv2021

Interpretable and Trustworthy Deepfake Detection via Dynamic Prototypes

In this paper we propose a novel human-centered approach for detecting forgery in face images, using dynamic prototypes as a form of visual explanations. Currently, most state-of-the-art deepfake detections are based on black-box models that process videos frame-by-frame for inference, and few closely examine their temporal inconsistencies. However, the existence of such temporal artifacts within deepfake videos is key in detecting and explaining deepfakes to a supervising human. To this end, we propose Dynamic Prototype Network (DPNet) -- an interpretable and effective solution that utilizes dynamic representations (i.e., prototypes) to explain deepfake temporal artifacts. Extensive experimental results show that DPNet achieves competitive predictive performance, even on unseen testing datasets such as Google's DeepFakeDetection, DeeperForensics, and Celeb-DF, while providing easy referential explanations of deepfake dynamics. On top of DPNet's prototypical framework, we further formulate temporal logic specifications based on these dynamics to check our model's compliance to desired temporal behaviors, hence providing trustworthiness for such critical detection systems.

cs.CV↗

arXiv2020

Towards Accurate Spatiotemporal COVID-19 Risk Scores using High Resolution Real-World Mobility Data

As countries look towards re-opening of economic activities amidst the ongoing COVID-19 pandemic, ensuring public health has been challenging. While contact tracing only aims to track past activities of infected users, one path to safe reopening is to develop reliable spatiotemporal risk scores to indicate the propensity of the disease. Existing works which aim to develop risk scores either rely on compartmental model-based reproduction numbers (which assume uniform population mixing) or develop coarse-grain spatial scores based on reproduction number (R0) and macro-level density-based mobility statistics. Instead, in this paper, we develop a Hawkes process-based technique to assign relatively fine-grain spatial and temporal risk scores by leveraging high-resolution mobility data based on cell-phone originated location signals. While COVID-19 risk scores also depend on a number of factors specific to an individual, including demography and existing medical conditions, the primary mode of disease transmission is via physical proximity and contact. Therefore, we focus on developing risk scores based on location density and mobility behaviour. We demonstrate the efficacy of the developed risk scores via simulation based on real-world mobility data. Our results show that fine-grain spatiotemporal risk scores based on high-resolution mobility data can provide useful insights and facilitate safe re-opening.

cs.LG↗

arXiv2020

LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT

Compressed sensing (CS) computed tomography has been proven to be important for several clinical applications, such as sparse-view computed tomography (CT), digital tomosynthesis and interior tomography. Traditional compressed sensing focuses on the design of handcrafted prior regularizers, which are usually image-dependent and time-consuming. Inspired by recently proposed deep learning-based CT reconstruction models, we extend the state-of-the-art LEARN model to a dual-domain version, dubbed LEARN++. Different from existing iteration unrolling methods, which only involve projection data in the data consistency layer, the proposed LEARN++ model integrates two parallel and interactive subnetworks to perform image restoration and sinogram inpainting operations on both the image and projection domains simultaneously, which can fully explore the latent relations between projection data and reconstructed images. The experimental results demonstrate that the proposed LEARN++ model achieves competitive qualitative and quantitative results compared to several state-of-the-art methods in terms of both artifact reduction and detail preservation.

physics.med-ph↗

arXiv2020

RACH in Self-Powered NB-IoT Networks: Energy Availability and Performance Evaluation

NarrowBand-Internet of Things (NB-IoT) is a new 3GPP radio access technology designed to provide better coverage for a massive number of low-throughput low-cost devices in delay-tolerant applications with low power consumption. To provide reliable connections with extended coverage, a repetition transmission scheme is introduced to NB-IoT during both Random Access CHannel (RACH) procedure and data transmission procedure. To avoid the difficulty in replacing the battery for IoT devices, the energy harvesting is considered as a promising solution to support energy sustainability in the NB-IoT network. In this work, we analyze RACH success probability in a self-powered NB-IoT network taking into account the repeated preamble transmissions and collisions, where each IoT device with data is active when its battery energy is sufficient to support the transmission. We model the temporal dynamics of the energy level as a birth-death process, derive the energy availability of each IoT device, and examine its dependence on the energy storage capacity and the repetition value. We show that in certain scenarios, the energy availability remains unchanged despite randomness in the energy harvesting. We also derive the exact expression for the RACH success probability of a {randomly chosen} IoT device under the derived energy availability, which is validated under different repetition values via simulations. We show that the repetition scheme can efficiently improve the RACH success probability in a light traffic scenario, but only slightly improves that performance with very inefficient channel resource utilization in a heavy traffic scenario.

eess.SP↗

arXiv2020

Multi-agent Trajectory Prediction with Fuzzy Query Attention

Trajectory prediction for scenes with multiple agents and entities is a challenging problem in numerous domains such as traffic prediction, pedestrian tracking and path planning. We present a general architecture to address this challenge which models the crucial inductive biases of motion, namely, inertia, relative motion, intents and interactions. Specifically, we propose a relational model to flexibly model interactions between agents in diverse environments. Since it is well-known that human decision making is fuzzy by nature, at the core of our model lies a novel attention mechanism which models interactions by making continuous-valued (fuzzy) decisions and learning the corresponding responses. Our architecture demonstrates significant performance gains over existing state-of-the-art predictive models in diverse domains such as human crowd trajectories, US freeway traffic, NBA sports data and physics datasets. We also present ablations and augmentations to understand the decision-making process and the source of gains in our model.

cs.LG↗

arXiv2020

Quantum Chaos in Topologically Massive Gravity

We study quantum chaos of rotating BTZ black holes in Topologically Massive gravity (TMG). We discuss the relationship between chaos parameters including Lyapunov exponents and butterfly velocities from shock wave calculations of out-of-time-order correlators (OTOC) and from pole-skipping analysis. We find a partial match between pole-skipping and the OTOC results in the high temperature regime. We also find that the velocity bound puts a chaos constraint on the gravitational Chern-Simons coupling.

hep-th↗

arXiv2020

CT Reconstruction with PDF: Parameter-Dependent Framework for Multiple Scanning Geometries and Dose Levels

Current mainstream of CT reconstruction methods based on deep learning usually needs to fix the scanning geometry and dose level, which will significantly aggravate the training cost and need more training data for clinical application. In this paper, we propose a parameter-dependent framework (PDF) which trains data with multiple scanning geometries and dose levels simultaneously. In the proposed PDF, the geometry and dose level are parameterized and fed into two multi-layer perceptrons (MLPs). The MLPs are leveraged to modulate the feature maps of CT reconstruction network, which condition the network outputs on different scanning geometries and dose levels. The experiments show that our proposed method can obtain competing performance similar to the original network trained with specific geometry and dose level, which can efficiently save the extra training cost for multiple scanning geometries and dose levels.

physics.med-ph↗

arXiv2020

Fourth-Order Nonlocal Tensor Decomposition Model for Spectral Computed Tomography

Spectral computed tomography (CT) can reconstruct spectral images from different energy bins using photon counting detectors (PCDs). However, due to the limited photons and counting rate in the corresponding spectral fraction, the reconstructed spectral images usually suffer from severe noise. In this paper, a fourth-order nonlocal tensor decomposition model for spectral CT image reconstruction (FONT-SIR) method is proposed. Similar patches are collected in both spatial and spectral dimensions simultaneously to form the basic tensor unit. Additionally, principal component analysis (PCA) is applied to extract latent features from the patches for a robust and efficient similarity measure. Then, low-rank and sparsity decomposition is performed on the produced fourth-order tensor unit, and the weighted nuclear norm and total variation (TV) norm are used to enforce the low-rank and sparsity constraints, respectively. The alternating direction method of multipliers (ADMM) is adopted to optimize the objective function. The experimental results with our proposed FONT-SIR demonstrates a superior qualitative and quantitative performance for both simulated and real data sets relative to several state-of-the-art methods, in terms of noise suppression and detail preservation.

physics.med-ph↗