arXiv subjects

Hu Chen

Publications and source records attributed to Hu Chen.

At least 55 records · Page 3Linked to original sources

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

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↗

arXiv2020

MAGIC: Manifold and Graph Integrative Convolutional Network for Low-Dose CT Reconstruction

Low-dose computed tomography (LDCT) scans, which can effectively alleviate the radiation problem, will degrade the imaging quality. In this paper, we propose a novel LDCT reconstruction network that unrolls the iterative scheme and performs in both image and manifold spaces. Because patch manifolds of medical images have low-dimensional structures, we can build graphs from the manifolds. Then, we simultaneously leverage the spatial convolution to extract the local pixel-level features from the images and incorporate the graph convolution to analyze the nonlocal topological features in manifold space. The experiments show that our proposed method outperforms both the quantitative and qualitative aspects of state-of-the-art methods. In addition, aided by a projection loss component, our proposed method also demonstrates superior performance for semi-supervised learning. The network can remove most noise while maintaining the details of only 10% (40 slices) of the training data labeled.

eess.IV↗

arXiv2020

Noise-Powered Disentangled Representation for Unsupervised Speckle Reduction of Optical Coherence Tomography Images

Due to its noninvasive character, optical coherence tomography (OCT) has become a popular diagnostic method in clinical settings. However, the low-coherence interferometric imaging procedure is inevitably contaminated by heavy speckle noise, which impairs both visual quality and diagnosis of various ocular diseases. Although deep learning has been applied for image denoising and achieved promising results, the lack of well-registered clean and noisy image pairs makes it impractical for supervised learning-based approaches to achieve satisfactory OCT image denoising results. In this paper, we propose an unsupervised OCT image speckle reduction algorithm that does not rely on well-registered image pairs. Specifically, by employing the ideas of disentangled representation and generative adversarial network, the proposed method first disentangles the noisy image into content and noise spaces by corresponding encoders. Then, the generator is used to predict the denoised OCT image with the extracted content features. In addition, the noise patches cropped from the noisy image are utilized to facilitate more accurate disentanglement. Extensive experiments have been conducted, and the results suggest that our proposed method is superior to the classic methods and demonstrates competitive performance to several recently proposed learning-based approaches in both quantitative and qualitative aspects.

eess.IV↗

arXiv2020

Learning Invariant Representation for Unsupervised Image Restoration

Recently, cross domain transfer has been applied for unsupervised image restoration tasks. However, directly applying existing frameworks would lead to domain-shift problems in translated images due to lack of effective supervision. Instead, we propose an unsupervised learning method that explicitly learns invariant presentation from noisy data and reconstructs clear observations. To do so, we introduce discrete disentangling representation and adversarial domain adaption into general domain transfer framework, aided by extra self-supervised modules including background and semantic consistency constraints, learning robust representation under dual domain constraints, such as feature and image domains. Experiments on synthetic and real noise removal tasks show the proposed method achieves comparable performance with other state-of-the-art supervised and unsupervised methods, while having faster and stable convergence than other domain adaption methods.

cs.CV↗

arXiv2019

Visual Attention Network for Low Dose CT

Noise and artifacts are intrinsic to low dose CT (LDCT) data acquisition, and will significantly affect the imaging performance. Perfect noise removal and image restoration is intractable in the context of LDCT due to the statistical and technical uncertainties. In this paper, we apply the generative adversarial network (GAN) framework with a visual attention mechanism to deal with this problem in a data-driven/machine learning fashion. Our main idea is to inject visual attention knowledge into the learning process of GAN to provide a powerful prior of the noise distribution. By doing this, both the generator and discriminator networks are empowered with visual attention information so they will not only pay special attention to noisy regions and surrounding structures but also explicitly assess the local consistency of the recovered regions. Our experiments qualitatively and quantitatively demonstrate the effectiveness of the proposed method with clinic CT images.

physics.med-ph↗

arXiv2019

Denoising of 3-D Magnetic Resonance Images Using a Residual Encoder-Decoder Wasserstein Generative Adversarial Network

Structure-preserved denoising of 3D magnetic resonance imaging (MRI) images is a critical step in medical image analysis. Over the past few years, many algorithms with impressive performances have been proposed. In this paper, inspired by the idea of deep learning, we introduce an MRI denoising method based on the residual encoder-decoder Wasserstein generative adversarial network (RED-WGAN). Specifically, to explore the structure similarity between neighboring slices, a 3D configuration is utilized as the basic processing unit. Residual autoencoders combined with deconvolution operations are introduced into the generator network. Furthermore, to alleviate the oversmoothing shortcoming of the traditional mean squared error (MSE) loss function, the perceptual similarity, which is implemented by calculating the distances in the feature space extracted by a pretrained VGG-19 network, is incorporated with the MSE and adversarial losses to form the new loss function. Extensive experiments are implemented to assess the performance of the proposed method. The experimental results show that the proposed RED-WGAN achieves performance superior to several state-of-the-art methods in both simulated and real clinical data. In particular, our method demonstrates powerful abilities in both noise suppression and structure preservation.

physics.med-ph↗

arXiv2018

Structural-elastic determination of the mechanical lifetime of biomolecules

The lifetime of protein domains and ligand-receptor complexes under force is crucial for mechanosensitive functions, while many aspects of how force affects the lifetime still remain poorly understood. Here, we report a new analytical expression of the force-dependent molecular lifetime to understand transitions overcoming a single barrier. Unlike previous models derived in the framework of Kramers theory that requires a presumed one-dimensional free energy landscape, our model is derived based on the structural-elastic properties of molecules which is not restricted by the shape and dimensionality of the underlying free energy landscape. Importantly, the parameters of this model provide direct information of the structural-elastic features of the molecules between the transition and the native states. We demonstrate the applications of this model by applying it to explain complex force-dependent lifetime data for several molecules reported in recent experiments, and predict the structural-elastic properties of the transition states of these molecules.

physics.bio-ph↗

arXiv2018

LEARN: Learned Experts' Assessment-based Reconstruction Network for Sparse-data CT

Compressive sensing (CS) has proved effective for tomographic reconstruction from sparsely collected data or under-sampled measurements, which are practically important for few-view CT, tomosynthesis, interior tomography, and so on. To perform sparse-data CT, the iterative reconstruction commonly use regularizers in the CS framework. Currently, how to choose the parameters adaptively for regularization is a major open problem. In this paper, inspired by the idea of machine learning especially deep learning, we unfold a state-of-the-art "fields of experts" based iterative reconstruction scheme up to a number of iterations for data-driven training, construct a Learned Experts' Assessment-based Reconstruction Network ("LEARN") for sparse-data CT, and demonstrate the feasibility and merits of our LEARN network. The experimental results with our proposed LEARN network produces a competitive performance with the well-known Mayo Clinic Low-Dose Challenge Dataset relative to several state-of-the-art methods, in terms of artifact reduction, feature preservation, and computational speed. This is consistent to our insight that because all the regularization terms and parameters used in the iterative reconstruction are now learned from the training data, our LEARN network utilizes application-oriented knowledge more effectively and recovers underlying images more favorably than competing algorithms. Also, the number of layers in the LEARN network is only 12, reducing the computational complexity of typical iterative algorithms by orders of magnitude.

physics.med-ph↗

arXiv2017

Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)

Given the potential X-ray radiation risk to the patient, low-dose CT has attracted a considerable interest in the medical imaging field. The current main stream low-dose CT methods include vendor-specific sinogram domain filtration and iterative reconstruction, but they need to access original raw data whose formats are not transparent to most users. Due to the difficulty of modeling the statistical characteristics in the image domain, the existing methods for directly processing reconstructed images cannot eliminate image noise very well while keeping structural details. Inspired by the idea of deep learning, here we combine the autoencoder, the deconvolution network, and shortcut connections into the residual encoder-decoder convolutional neural network (RED-CNN) for low-dose CT imaging. After patch-based training, the proposed RED-CNN achieves a competitive performance relative to the-state-of-art methods in both simulated and clinical cases. Especially, our method has been favorably evaluated in terms of noise suppression, structural preservation and lesion detection.

physics.med-ph↗

arXiv2017

Effective face landmark localization via single deep network

In this paper, we propose a novel face alignment method using single deep network (SDN) on existing limited training data. Rather than using a max-pooling layer followed one convolutional layer in typical convolutional neural networks (CNN), SDN adopts a stack of 3 layer groups instead. Each group layer contains two convolutional layers and a max-pooling layer, which can extract the features hierarchically. Moreover, an effective data augmentation strategy and corresponding training skills are also proposed to over-come the lack of training images on COFW and 300-W da-tasets. The experiment results show that our method outper-forms state-of-the-art methods in both detection accuracy and speed.

cs.CV↗

arXiv2016

Low-dose CT denoising with convolutional neural network

To reduce the potential radiation risk, low-dose CT has attracted much attention. However, simply lowering the radiation dose will lead to significant deterioration of the image quality. In this paper, we propose a noise reduction method for low-dose CT via deep neural network without accessing original projection data. A deep convolutional neural network is trained to transform low-dose CT images towards normal-dose CT images, patch by patch. Visual and quantitative evaluation demonstrates a competing performance of the proposed method.

physics.med-ph↗

arXiv2016

Low-Dose CT via Deep Neural Network

In order to reduce the potential radiation risk, low-dose CT has attracted more and more attention. However, simply lowering the radiation dose will significantly degrade the imaging quality. In this paper, we propose a noise reduction method for low-dose CT via deep learning without accessing the original projection data. An architecture of deep convolutional neural network was considered to map the low-dose CT images into its corresponding normal-dose CT images patch by patch. Qualitative and quantitative evaluations demonstrate a state-the-art performance of the proposed method.

physics.med-ph↗

arXiv2015

Revisiting the anomalous bending elasticity of sharply bent DNA

Several recent experiments suggest that sharply bent DNA has a surprisingly high bending flexibility, but the cause of this flexibility is poorly understood. Although excitation of flexible defects can explain these results, whether such excitation can occur with the level of DNA bending in these experiments remains unclear. Intriguingly, the DNA contained preexisting nicks in most of these experiments but whether nicks might play a role in flexibility has never been considered in the interpretation of experimental results. Here, using full-atom molecular dynamics simulations, we show that nicks promote DNA basepair disruption at the nicked sites, which drastically reduces DNA bending energy. In addition, lower temperatures suppress the nick-dependent basepair disruption. In the absence of nicks, basepair disruption can also occur but requires a higher level of DNA bending. Therefore, basepair disruption inside B-form DNA can be suppressed if the DNA contains preexisting nicks. Overall, our results suggest that the reported mechanical anomaly of sharply bent DNA is likely dependent on preexisting nicks, therefore the intrinsic mechanisms of sharply bent nick-free DNA remain an open question.

physics.bio-ph↗

arXiv2015

An SVD-based Fragile Watermarking Scheme With Grouped Blocks

This paper proposes a novel fragile watermarking scheme for digital image authentication which is based on Singular Value Decomposition(SVD) and grouped blocks. The watermark bits which include two types of bits are inserted into the least significant bit(LSB) plane of the host image using the adaptive chaotic map to determine the positions. The groped blocks break the block-wise independence and therefore can withstand the Vector Quantization attack(VQ attack). The inserting positions are related to the statistical information of image block data, in order to increase the security and provide an auxiliary way to authenticate the image data. The effectiveness of the proposed scheme is checked by a variety of attacks, and the experimental results prove that it has a remarkable tamper detection ability and also has a precise locating ability.

cs.CR↗

arXiv2009

Temperature dependence of circular DNA topological states

Circular double stranded DNA has different topological states which are defined by their linking numbers. Equilibrium distribution of linking numbers can be obtained by closing a linear DNA into a circle by ligase. Using Monte Carlo simulation, we predict the temperature dependence of the linking number distribution of small circular DNAs. Our predictions are based on flexible defect excitations resulted from local melting or unstacking of DNA base pairs. We found that the reduced bending rigidity alone can lead to measurable changes of the variance of linking number distribution of short circular DNAs. If the defect is accompanied by local unwinding, the effect becomes much more prominent. The predictions can be easily investigated in experiments, providing a new method to study the micromechanics of sharply bent DNAs and the thermal stability of specific DNA sequences. Furthermore, the predictions are directly applicable to the studies of binding of DNA distorting proteins that can locally reduce DNA rigidity, form DNA kinks, or introduce local unwinding.

q-bio.BM↗

arXiv2008

Effects of kink and flexible hinge defects on mechanical responses of short double stranded DNA molecules

We predict various detectable mechanical responses to the presence of local DNA defects which are defined as short DNA segments exhibiting mechanical properties obviously different from the 50 nm persistence length based semiflexible polymer model. The defects discussed are kinks and flexible hinges either permanently fixed on DNA or thermally excited. Their effects on extension shift, the effective persistence length, the end-to-end distance distribution, and the cyclization probability are computed using a transfer-matrix method. Our predictions will be useful in future experimental designs to study DNA nicks or mismatch base pairs, mechanics of specific DNA sequences, and specific DNA-protein interaction using magnetic tweezer, fluorescence resonance energy transfer or plasmon resonance technique, and the traditional biochemistry cyclization probability measurements.

q-bio.BM↗