arXiv subjects

Lei Li

Publications and source records attributed to Lei Li.

At least 757 records · Page 42Linked to original sources

arXiv2019

Projection Super-resolution Based on Convolutional Neural Network for Computed Tomography

The improvement of computed tomography (CT) image resolution is beneficial to the subsequent medical diagnosis, but it is usually limited by the scanning devices and great expense. Convolutional neural network (CNN)-based methods have achieved promising ability in super-resolution. However, existing methods mainly focus on the super-resolution of reconstructed image and do not fully explored the approach of super-resolution from projection-domain. In this paper, we studied the characteristic of projection and proposed a CNN-based super-resolution method to establish the mapping relationship of low- and high-resolution projection. The network label is high-resolution projection and the input is its corresponding interpolation data after down sampling. FDK algorithm is utilized for three-dimensional image reconstruction and one slice of reconstruction image is taken as an example to evaluate the performance of the proposed method. Qualitative and quantitative results show that the proposed method is potential to improve the resolution of projection and enables the reconstructed image with higher quality.

physics.med-ph↗

arXiv2019

A Sinogram Inpainting Method based on Generative Adversarial Network for Limited-angle Computed Tomography

Limited-angle computed tomography (CT) image reconstruction is a challenging reconstruction problem in the fields of CT. With the development of deep learning, the generative adversarial network (GAN) perform well in image restoration by approximating the distribution of training sample data. In this paper, we proposed an effective GAN-based inpainting method to restore the missing sinogram data for limited-angle scanning. To estimate the missing data, we design the generator and discriminator of the patch-GAN and train the network to learn the data distribution of the sinogram. We obtain the reconstructed image from the restored sinogram by filtered back projection and simultaneous algebraic reconstruction technique with total variation. Experimental results show that serious artifacts caused by missing projection data can be reduced by the proposed method, and it is hopeful to solve the reconstruction problem of 60 degrees limited scanning angle.

physics.med-ph↗

arXiv2019

Atrial Scar Quantification via Multi-scale CNN in the Graph-cuts Framework

Late gadolinium enhancement magnetic resonance imaging (LGE MRI) appears to be a promising alternative for scar assessment in patients with atrial fibrillation (AF). Automating the quantification and analysis of atrial scars can be challenging due to the low image quality. In this work, we propose a fully automated method based on the graph-cuts framework, where the potentials of the graph are learned on a surface mesh of the left atrium (LA) using a multi-scale convolutional neural network (MS-CNN). For validation, we have employed fifty-eight images with manual delineations. MS-CNN, which can efficiently incorporate both the local and global texture information of the images, has been shown to evidently improve the segmentation accuracy of the proposed graph-cuts based method. The segmentation could be further improved when the contribution between the t-link and n-link weights of the graph is balanced. The proposed method achieves a mean accuracy of 0.856 +- 0.033 and mean Dice score of 0.702 +- 0.071 for LA scar quantification. Compared with the conventional methods, which are based on the manual delineation of LA for initialization, our method is fully automatic and has demonstrated significantly better Dice score and accuracy (p < 0.01). The method is promising and can be useful in diagnosis and prognosis of AF.

cs.CV↗

arXiv2019

Evaluation of Algorithms for Multi-Modality Whole Heart Segmentation: An Open-Access Grand Challenge

Knowledge of whole heart anatomy is a prerequisite for many clinical applications. Whole heart segmentation (WHS), which delineates substructures of the heart, can be very valuable for modeling and analysis of the anatomy and functions of the heart. However, automating this segmentation can be arduous due to the large variation of the heart shape, and different image qualities of the clinical data. To achieve this goal, a set of training data is generally needed for constructing priors or for training. In addition, it is difficult to perform comparisons between different methods, largely due to differences in the datasets and evaluation metrics used. This manuscript presents the methodologies and evaluation results for the WHS algorithms selected from the submissions to the Multi-Modality Whole Heart Segmentation (MM-WHS) challenge, in conjunction with MICCAI 2017. The challenge provides 120 three-dimensional cardiac images covering the whole heart, including 60 CT and 60 MRI volumes, all acquired in clinical environments with manual delineation. Ten algorithms for CT data and eleven algorithms for MRI data, submitted from twelve groups, have been evaluated. The results show that many of the deep learning (DL) based methods achieved high accuracy, even though the number of training datasets was limited. A number of them also reported poor results in the blinded evaluation, probably due to overfitting in their training. The conventional algorithms, mainly based on multi-atlas segmentation, demonstrated robust and stable performance, even though the accuracy is not as good as the best DL method in CT segmentation. The challenge, including the provision of the annotated training data and the blinded evaluation for submitted algorithms on the test data, continues as an ongoing benchmarking resource via its homepage (\url{www.sdspeople.fudan.edu.cn/zhuangxiahai/0/mmwhs/}).

cs.CV↗

arXiv2019

Evanescent Field Functional Cu3-xP Nanoparticles as Effective Saturable Absorbers with high Repeatability for Femtosecond Soliton Pulse generation

Recently, a new emerging field about heavily-doped colloidal plasmonic nanocrystals (NCs) has attracted great attention due to their lower and expediently adjustable free carrier densities, lower and tunable LSPR band in the spectral range from NIR to MIR and higher optical nonlinearity. These new kinds of plasmonic materials will show huge potential and opportunities for nonlinear optical applications, such as ultrafast switching, nonlinear sensing and pulse laser generation. In this work, we demonstrate that high-quality mode-locking and Q-switching pulses at 1560 nm can both be generated by using controllable concentration of Cu3-xP NCs solution and fabricating evanescently interacted saturable absorbers. Furthermore, the plasmonic NCs material has good reproduction for fabricating SA devices and promising potential for large-scale industrial production. Our results may attract great attention for further investigations of heavily-doped plasmonic NCs as next generation, cheap and solution-processed element for fascinating applications in optoelectronic devices.

physics.app-ph↗

arXiv2018

Sketch-R2CNN: An Attentive Network for Vector Sketch Recognition

Freehand sketching is a dynamic process where points are sequentially sampled and grouped as strokes for sketch acquisition on electronic devices. To recognize a sketched object, most existing methods discard such important temporal ordering and grouping information from human and simply rasterize sketches into binary images for classification. In this paper, we propose a novel single-branch attentive network architecture RNN-Rasterization-CNN (Sketch-R2CNN for short) to fully leverage the dynamics in sketches for recognition. Sketch-R2CNN takes as input only a vector sketch with grouped sequences of points, and uses an RNN for stroke attention estimation in the vector space and a CNN for 2D feature extraction in the pixel space respectively. To bridge the gap between these two spaces in neural networks, we propose a neural line rasterization module to convert the vector sketch along with the attention estimated by RNN into a bitmap image, which is subsequently consumed by CNN. The neural line rasterization module is designed in a differentiable way to yield a unified pipeline for end-to-end learning. We perform experiments on existing large-scale sketch recognition benchmarks and show that by exploiting the sketch dynamics with the attention mechanism, our method is more robust and achieves better performance than the state-of-the-art methods.

cs.CV↗

arXiv2018

CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling

In real-world applications of natural language generation, there are often constraints on the target sentences in addition to fluency and naturalness requirements. Existing language generation techniques are usually based on recurrent neural networks (RNNs). However, it is non-trivial to impose constraints on RNNs while maintaining generation quality, since RNNs generate sentences sequentially (or with beam search) from the first word to the last. In this paper, we propose CGMH, a novel approach using Metropolis-Hastings sampling for constrained sentence generation. CGMH allows complicated constraints such as the occurrence of multiple keywords in the target sentences, which cannot be handled in traditional RNN-based approaches. Moreover, CGMH works in the inference stage, and does not require parallel corpora for training. We evaluate our method on a variety of tasks, including keywords-to-sentence generation, unsupervised sentence paraphrasing, and unsupervised sentence error correction. CGMH achieves high performance compared with previous supervised methods for sentence generation. Our code is released at https://github.com/NingMiao/CGMH

cs.CL↗

arXiv2018

Face Presentation Attack Detection in Learned Color-liked Space

Face presentation attack detection (PAD) has become a thorny problem for biometric systems and numerous countermeasures have been proposed to address it. However, majority of them directly extract feature descriptors and distinguish fake faces from the real ones in existing color spaces (e.g. RGB, HSV and YCbCr). Unfortunately, it is unknown for us which color space is the best or how to combine different spaces together. To make matters worse, the real and fake faces are overlapped in existing color spaces. So, in this paper, a learned distinguishable color-liked space is generated to deal with the problem of face PAD. More specifically, we present an end-to-end deep learning network that can map existing color spaces to a new learned color-liked space. Inspired by the generator of generative adversarial network (GAN), the proposed network consists of a space generator and a feature extractor. When training the color-liked space, a new triplet combination mechanism of points-to-center is explored to maximize interclass distance and minimize intraclass distance, and also keep a safe margin between the real and presented fake faces. Extensive experiments on two standard face PAD databases, i.e., Relay-Attack and OULU-NPU, indicate that our proposed color-liked space analysis based countermeasure significantly outperforms the state-of-the-art methods and show excellent generalization capability.

cs.CV↗

arXiv2018

Atrial fibrosis quantification based on maximum likelihood estimator of multivariate images

We present a fully-automated segmentation and quantification of the left atrial (LA) fibrosis and scars combining two cardiac MRIs, one is the target late gadolinium-enhanced (LGE) image, and the other is an anatomical MRI from the same acquisition session. We formulate the joint distribution of images using a multivariate mixture model (MvMM), and employ the maximum likelihood estimator (MLE) for texture classification of the images simultaneously. The MvMM can also embed transformations assigned to the images to correct the misregistration. The iterated conditional mode algorithm is adopted for optimization. This method first extracts the anatomical shape of the LA, and then estimates a prior probability map. It projects the resulting segmentation onto the LA surface, for quantification and analysis of scarring. We applied the proposed method to 36 clinical data sets and obtained promising results (Accuracy: $0.809\pm .150$, Dice: $0.556\pm.187$). We compared the method with the conventional algorithms and showed an evidently and statistically better performance ($p<0.03$).

cs.CV↗

arXiv2018

Atrial scars segmentation via potential learning in the graph-cuts framework

Late Gadolinium Enhancement Magnetic Resonance Imaging (LGE MRI) emerged as a routine scan for patients with atrial fibrillation (AF). However, due to the low image quality automating the quantification and analysis of the atrial scars is challenging. In this study, we pro-posed a fully automated method based on the graph-cuts framework, where the potential of the graph is learned on a surface mesh of the left atrium (LA) using an equidistant projection and a Deep Neural Network (DNN). For validation, we employed 100 datasets with manual delineation. The results showed that the performance of the proposed method improved and converged with respect to the increased size of training patches, which provide important features of the structural and texture information learned by the DNN. The segmentation could be further improved when the contribution from the t-link and n-link is balanced, thanks to inter-relationship learned by the DNN for the graph-cuts algorithm. Compared with the published methods which mostly acquired manual delineation of the LA or LA wall, our method is fully automatic and demonstrated evidently better results with statistical significance. Finally, the accuracy of quantifying the scars assessed by the Dice score was 0.570. The results are promising and the method can be useful in diagnosis and prognosis of AF.

cs.CV↗

arXiv2018

Dynamics of spin-orbit-coupled cold atomic gases in a Floquet lattice with an impurity

In this study, we have studied the quantum tunneling of a single spin-orbit-coupled atom held in a periodically modulated optical lattice with an impurity. At the pseudocollapse points of quasienergy bands, where the dynamical localization takes place globally, two types of local second-order tunneling processes appear beyond expectation between the two nearest-neighbor sites of the impurity with the spin unchanged and with impurity site population negligible all the time, when the impurity potential is far off-resonant with the driving field. Though tunneling behaviors of the two types seem to be the same, they are believed to involve two distinct mechanisms: one is related to spin-independent process, while the other is to spin-dependent tunneling process. The two types of second-order processes can be identified by means of resonant tunneling with or without spin-flipping by tuning the impurity potential to be in resonance with the driving field. In the Floquet picture, the second-order processes are manifested as subtle and fine avoided crossings of quasienergy spectrums near the pseudocollapse region. These results are confirmed analytically on the basis of effective three-site model and multiple-time-scale asymptotic perturbative method, and may be exploited for engineering the spin-dependent quantum transport in realistic experiments.

quant-ph↗

arXiv2018

Numerical study of ergodicity for the overdamped Generalized Langevin Equation with fractional noise

The Generalized Langevin Equation, in history, arises as a natural fix for the rather traditional Langevin equation when the random force is no longer memoryless. It has been proved that with fractional Gaussian noise (fGn) mostly considered by biologists, the overdamped Generalized Langevin equation satisfying fluctuation-dissipation theorem can be written as a fractional stochastic differential equation (FSDE). While the ergodicity is clear for linear forces, it remains less transparent for nonlinear forces. In this work, we present both a direct and a fast algorithm respectively to this FSDE model. The strong orders of convergence are proved for both schemes, where the role of the memory effects can be clearly observed. We verify the convergence theorems using linear forces, and then present the ergodicity study of the double well potentials in both 1D and 2D setups.

math.NA↗

arXiv2018

Novel development of dissipative-soliton-resonance pulses with pump power in an all-normal-dispersion fiber laser

Evolution of dissipative-soliton-resonance (DSR) pulses in an all-normal-dispersion fiber laser with pump power under various operation conditions are experimentally studied. The fiber laser is mode-locked by using a nonlinear fiber loop mirror. Apart from the typical pulse broadening due to the peak power clamping effect, pulse breaking was observed. In addition, pulse narrowing with pump power increasing was observed. All the incompatible evolution of DSR pulses could be attributed to the multiple parameters change due to pump power increasing under specific operation conditions.

physics.optics↗

arXiv2018

Structures and Anomalies of Water

Introduction of the principles of the asymmetrical, short-range O:H-O coupled oscillater pair and the basic rule for water ice, which reconciles the structure and anomalies of water ice.

physics.chem-ph↗

arXiv2018

On Tree-Based Neural Sentence Modeling

Neural networks with tree-based sentence encoders have shown better results on many downstream tasks. Most of existing tree-based encoders adopt syntactic parsing trees as the explicit structure prior. To study the effectiveness of different tree structures, we replace the parsing trees with trivial trees (i.e., binary balanced tree, left-branching tree and right-branching tree) in the encoders. Though trivial trees contain no syntactic information, those encoders get competitive or even better results on all of the ten downstream tasks we investigated. This surprising result indicates that explicit syntax guidance may not be the main contributor to the superior performances of tree-based neural sentence modeling. Further analysis show that tree modeling gives better results when crucial words are closer to the final representation. Additional experiments give more clues on how to design an effective tree-based encoder. Our code is open-source and available at https://github.com/ExplorerFreda/TreeEnc.

cs.CL↗

arXiv2018

Fast Sketch Segmentation and Labeling with Deep Learning

We present a simple and efficient method based on deep learning to automatically decompose sketched objects into semantically valid parts. We train a deep neural network to transfer existing segmentations and labelings from 3D models to freehand sketches without requiring numerous well-annotated sketches as training data. The network takes the binary image of a sketched object as input and produces a corresponding segmentation map with per-pixel labelings as output. A subsequent post-process procedure with multi-label graph cuts further refines the segmentation and labeling result. We validate our proposed method on two sketch datasets. Experiments show that our method outperforms the state-of-the-art method in terms of segmentation and labeling accuracy and is significantly faster, enabling further integration in interactive drawing systems. We demonstrate the efficiency of our method in a sketch-based modeling application that automatically transforms input sketches into 3D models by part assembly.

cs.GR↗

arXiv2018

Large time behaviors of upwind schemes by jump processes

We revisit the traditional upwind schemes for linear conservation laws in the viewpoint of jump processes, allowing studying upwind schemes using probabilistic tools. In particular, for Fokker-Planck equations on $\mathbb{R}$, in the case of weak confinement, we show that the solution of upwind scheme converges to a stationary solution. In the case of strong confinement, using a discrete Poincaré inequality, we prove that the $O(h)$ numeric error under $\ell^1$ norm is uniform in time, and establish the uniform exponential convergence to the steady states. Compared with the traditional results of exponential convergence of upwind schemes, our result is in the whole space without boundary. We also establish similar results on torus for which the stationary solution of the scheme does not have detailed balance. This work shows an interesting connection between standard numerical methods and time continuous Markov chains, and could motivate better understanding of numerical analysis for conservation laws.

math.NA↗

arXiv2018

Microfluidic control of nucleation and growth of calcite

The nucleation and growth of calcite is an important research in scientific and industrial field. Both the macroscopic and microscopic observation of calcite growth have been reported. Now, with the development of microfluidic device, we could focus the nucleation and growth of one single calcite. By changing the flow rate of fluid, the concentration of fluid is controlled. We introduced a new method to study calcite growth in situ and measured the growth rate of calcite in microfluidic channel.

physics.chem-ph↗