arXiv subjects

Kang Zhou

Publications and source records attributed to Kang Zhou.

At least 91 records · Page 5Linked to original sources

arXiv2020

High signal-to-noise ratio reconstruction of low bit-depth optical coherence tomography using deep learning

Reducing the bit-depth is an effective approach to lower the cost of optical coherence tomography (OCT) systems and increase the transmission efficiency in data acquisition and telemedicine. However, a low bit-depth will lead to the degeneration of the detection sensitivity thus reduce the signal-to-noise ratio (SNR) of OCT images. In this paper, we propose to use deep learning for the reconstruction of the high SNR OCT images from the low bit-depth acquisition. Its feasibility was preliminarily evaluated by applying the proposed method to the quantized $3\sim8$-bit data from native 12-bit interference fringes. We employed a pixel-to-pixel generative adversarial network architecture in the low to high bit-depth OCT image transition. Retinal OCT data of a healthy subject from a homemade spectral-domain OCT system was used in the study. Extensively qualitative and quantitative results show this deep-learning-based approach could significantly improve the SNR of the low bit-depth OCT images especially at the choroidal region. Superior similarity and SNR between the reconstructed images and the original 12-bit OCT images could be derived when the bit-depth $\geq 5$. This work demonstrates the proper integration of OCT and deep learning could benefit the development of healthcare in low-resource settings.

eess.IV↗

arXiv2020

Sparse-GAN: Sparsity-constrained Generative Adversarial Network for Anomaly Detection in Retinal OCT Image

With the development of convolutional neural network, deep learning has shown its success for retinal disease detection from optical coherence tomography (OCT) images. However, deep learning often relies on large scale labelled data for training, which is oftentimes challenging especially for disease with low occurrence. Moreover, a deep learning system trained from data-set with one or a few diseases is unable to detect other unseen diseases, which limits the practical usage of the system in disease screening. To address the limitation, we propose a novel anomaly detection framework termed Sparsity-constrained Generative Adversarial Network (Sparse-GAN) for disease screening where only healthy data are available in the training set. The contributions of Sparse-GAN are two-folds: 1) The proposed Sparse-GAN predicts the anomalies in latent space rather than image-level; 2) Sparse-GAN is constrained by a novel Sparsity Regularization Net. Furthermore, in light of the role of lesions for disease screening, we present to leverage on an anomaly activation map to show the heatmap of lesions. We evaluate our proposed Sparse-GAN on a publicly available dataset, and the results show that the proposed method outperforms the state-of-the-art methods.

cs.CV↗

arXiv2020

Digital resolution enhancement in low transverse sampling optical coherence tomography angiography using deep learning

Optical coherence tomography angiography (OCTA) requires high transverse sampling density for visualizing retinal and choroidal capillaries. Low transverse sampling causes resolution degradation, such as the angiograms in wide-field OCTA. In this paper, we propose to address this problem using deep learning. We conducted extensive experiments on converting the centrally cropped 3 x 3 mm2 field of view (FOV) of the 8 x 8 mm2 foveal OCTA images (a sampling density of 22.9 $μ$m) to the native 3 x 3 mm2 en face OCTA images (a sampling density of 12.2 $μ$m). We employed a cycle-consistent adversarial network architecture in this conversion. The quantitative analysis using the perceptual similarity measures shows the generated OCTA images are closer to the native 3 x 3 mm2 scans. Besides, the results show the proposed method could also enhance signal-to-noise ratio. We further applied our method to enhance diseased cases and calculate vascular biomarkers, which demonstrates its generalization performance and clinical perspective.

eess.IV↗

arXiv2019

Expansion of Einstein-Yang-Mills theory by Differential Operators

The factorization form of the integrands in the Cachazo-He-Yuan (CHY) formalism makes the generalized Kawai-Lewellen-Tye (KLT) relations manifest, thus amplitudes of one theory can be expanded in terms of the amplitudes of another theory. Although this claim seems a rather natural consequence of the above structure, finding the exact expansion coefficients to express an amplitude in terms of another amplitudes is, nonetheless, a nontrivial task despite many efforts devoted to it in the literature. In this paper, we propose a new strategy based in using the differential operators introduced by Cheung, Shen and Wen, and taking advantage of the fact these operators already relate the amplitudes of different theories. Using this new method, expansion coefficients can be found effectively.

hep-th↗

arXiv2019

Towards Compact and Real-Time Terahertz Dual-Comb Spectroscopy Employing a Self-Detection Scheme

Due to its fast and high resolution characteristics, dual-comb spectroscopy has attracted an increasing amount of interest since its first demonstration. In the terahertz frequency range where abundant absorption lines (finger prints) of molecules are located, multiheterodyne spectroscopy that employs the dual-comb technique shows an advantage in real-time spectral detection over the traditional Fourier transform infrared or time domain spectroscopies. Here, we demonstrate compact terahertz dual-comb spectroscopy based on quantum cascade lasers (QCLs). In our experiment, two free-running QCLs generate approximately 120 GHz wide combs centered at 4.2 THz, with slightly different repetition frequencies. We observe that $\sim$490 nW terahertz power coupling of one laser into the other suffices for laser-self-detecting the dual-comb spectrum that is registered by a microwave spectrum analyzer. Furthermore, we demonstrate practical terahertz transmission dual-comb spectroscopy with our device, by implementing a short air path at room temperature. Spectra are shown of semiconductor samples and of moist air, the latter allowing rapid monitoring of the relative humidity. Our devices should be readily extendable to perform imaging, microscopy and near-field microscopy in the terahertz regime.

physics.optics↗

arXiv2019

BioNet: Infusing Biomarker Prior into Global-to-Local Network for Choroid Segmentation in Optical Coherence Tomography Images

Choroid is the vascular layer of the eye, which is directly related to the incidence and severity of many ocular diseases. Optical Coherence Tomography (OCT) is capable of imaging both the cross-sectional view of retina and choroid, but the segmentation of the choroid region is challenging because of the fuzzy choroid-sclera interface (CSI). In this paper, we propose a biomarker infused global-to-local network (BioNet) for choroid segmentation, which segments the choroid with higher credibility and robustness. Firstly, our method trains a biomarker prediction network to learn the features of the biomarker. Then a global multi-layers segmentation module is applied to segment the OCT image into 12 layers. Finally, the global multi-layered result and the original OCT image are fed into a local choroid segmentation module to segment the choroid region with the biomarker infused as regularizer. We conducted comparison experiments with the state-of-the-art methods on a dataset (named AROD). The experimental results demonstrate the superiority of our method with $90.77\%$ Dice-index and 6.23 pixels Average-unsigned-surface-detection-error, etc.

cs.CV↗

arXiv2019

Perceptual-assisted Adversarial Adaptation for Choroid Segmentation in optical coherence tomography

Accurate choroid segmentation in optical coherence tomography (OCT) image is vital because the choroid thickness is a major quantitative biomarker of many ocular diseases. Deep learning has shown its superiority in the segmentation of the choroid region but subjects to the performance degeneration caused by the domain discrepancies (e.g., noise level and distribution) among datasets obtained from the OCT devices of different manufacturers. In this paper, we present an unsupervised perceptual-assisted adversarial adaptation (PAAA) framework for efficiently segmenting the choroid area by narrowing the domain discrepancies between different domains. The adversarial adaptation module in the proposed framework encourages the prediction structure information of the target domain to be similar to that of the source domain. Besides, a perceptual loss is employed for matching their shape information (the curvatures of Bruch's membrane and choroid-sclera interface) which can result in a fine boundary prediction. The results of quantitative experiments show that the proposed PAAA segmentation framework outperforms other state-of-the-art methods.

eess.IV↗

arXiv2019

Assessment of Generative Adversarial Networks Model for Synthetic Optical Coherence Tomography Images of Retinal Disorders

Purpose: To assess whether a generative adversarial network (GAN) could synthesize realistic optical coherence tomography (OCT) images that satisfactorily serve as the educational images for retinal specialists and the training datasets for the classification of various retinal disorders using deep learning (DL). Methods: The GANs architecture was adopted to synthesis high-resolution OCT images training on a publicly available OCT dataset including urgent referrals (choroidal neovascularization and diabetic macular edema) and non-urgent referrals (normal and drusen). 400 real and synthetic OCT images were evaluated by 2 retinal specialists to assess image quality. We further trained 2 DL models on either real or synthetic datasets and compared the performance of urgent vs nonurgent referrals diagnosis tested on a local (1000 images from the public dataset) and clinical validation dataset (278 images from Shanghai Shibei Hospital). Results: The image quality of real vs synthetic OCT images was similar as assessed by 2 retinal specialists. The accuracy of discrimination as real vs synthetic OCT images was 59.50% for retinal specialist 1 and 53.67% for retinal specialist 2. For the local dataset, the DL model trained on real (DL_Model_R) and synthetic OCT images (DL_Model_S) had an area under the curve (AUC) of 0.99, and 0.98 respectively. For the clinical dataset, the AUC was 0.94 for DL_Model_R, 0.90 for DL_Model_S. Conclusions: The GAN-synthetic OCT images can be used by clinicians for educational purposes and developing DL algorithms. Translational Relevance: The medical image synthesis based on GANs is promising in human and machine to fulfill clinical tasks.

physics.med-ph↗

arXiv2019

Eliminating Shadow Artifacts via Generative Inpainting Networks to Quantify Vascular Changes of the Choroid

Shadow artifacts from retinal vessels hinder the development of quantitative choroidal biomarkers in Optical Coherence Tomography (OCT), which limits the clinical applications of the choroidal OCT to the measures of layer thickness. In this paper, we present a novel framework that could eliminate the retinal shadows and realize the quantification of choroidal vasculature. Different from existing methods, we convert the shadow elimination into an object removal task, which can be handled by image inpainting techniques. We adopt and finetune a two-stage generative inpainting network which connects the edges of the vessels ahead of refilling the shadow-contaminated areas. It shows surpassing performance in repairing the choroidal vasculature compared with traditional inpainting algorithms. We further verify the feasibility of the proposed frame using a prospective observational study, which detects the choroidal vascular changes related to the Intra-Ocular Pressure (IOP) elevation of 34 healthy volunteers. As the average IOP increases from $15.84\pm1.99$ mmHg to $34.48\pm5.35$ mmHg, we achieve the decreases of the choroidal vessel density and flow index from $0.491\pm0.020$ to $0.463\pm0.019$ and from $0.336\pm0.025$ to $0.300\pm0.019$, respectively.

physics.med-ph↗

arXiv2019

Unified web for expansions of amplitudes

In this paper, we demonstrate that using differential operators one can construct the complete unified web for expansions of amplitudes for a wide range of theories. We first re-derive the expansion of multi-trace Einstein-Yang-Mills amplitudes to Kleiss-Kuijf basis of color-ordered Yang-Mills amplitudes, by applying proper differential operators which modify the coefficients in the recursive expansion of single-trace Einstein-Yang-Mills amplitudes. Next, through differential operators which act on amplitudes only, we obtain expansions of amplitudes of Yang-Mills theory, Yang-Mills-scalar theory, $ϕ^4$ theory, non-linear sigma model, bi-adjoint scalar theory, Born-Infeld theory, Dirac-Born-Infeld theory and special Galileon theory. Then, together with other results in literatures, the complete unified web is achieved. This web for expansions is the dual version of the unified web for differential operators. Thus, connections among amplitudes of a variety of theories, which are reflected by Cachazo-He-Yuan integrands and differential operators previously, can also be represented by expansions. We also find that amplitudes of all theories in the web can be expanded to double color-ordered bi-adjoint scalar amplitudes in the universal double copy formula.

hep-th↗

arXiv2019

Expansion of tree amplitudes for EM and other theories

The expansions of tree-level amplitudes for one theory into amplitudes for another theory, which have been studied in various recent literatures, exhibit hidden connections between different theories that are invisible in traditional Lagrangian formulism of quantum field theory. In this paper, the general expansion of tree EM (Einstein-Maxwell) amplitudes into KK basis of tree YM (Yang-Mills) amplitudes have been derived by applying the method based on differential operators. The obtained coefficients are shared by the expansion of tree $ϕ^4$ amplitudes into tree BS (bi-adjoint scalar) amplitudes, the expansion of tree sYMS (special Yang-Mills-scalar) amplitudes into tree BS amplitudes, as well the expansion of tree DBI (Dirac-Born-Infeld) amplitudes into tree special extended DBI amplitudes.

hep-th↗

arXiv2019

CE-Net: Context Encoder Network for 2D Medical Image Segmentation

Medical image segmentation is an important step in medical image analysis. With the rapid development of convolutional neural network in image processing, deep learning has been used for medical image segmentation, such as optic disc segmentation, blood vessel detection, lung segmentation, cell segmentation, etc. Previously, U-net based approaches have been proposed. However, the consecutive pooling and strided convolutional operations lead to the loss of some spatial information. In this paper, we propose a context encoder network (referred to as CE-Net) to capture more high-level information and preserve spatial information for 2D medical image segmentation. CE-Net mainly contains three major components: a feature encoder module, a context extractor and a feature decoder module. We use pretrained ResNet block as the fixed feature extractor. The context extractor module is formed by a newly proposed dense atrous convolution (DAC) block and residual multi-kernel pooling (RMP) block. We applied the proposed CE-Net to different 2D medical image segmentation tasks. Comprehensive results show that the proposed method outperforms the original U-Net method and other state-of-the-art methods for optic disc segmentation, vessel detection, lung segmentation, cell contour segmentation and retinal optical coherence tomography layer segmentation.

cs.CV↗

arXiv2018

Multi-Cell Multi-Task Convolutional Neural Networks for Diabetic Retinopathy Grading

Diabetic Retinopathy (DR) is a non-negligible eye disease among patients with Diabetes Mellitus, and automatic retinal image analysis algorithm for the DR screening is in high demand. Considering the resolution of retinal image is very high, where small pathological tissues can be detected only with large resolution image and large local receptive field are required to identify those late stage disease, but directly training a neural network with very deep architecture and high resolution image is both time computational expensive and difficult because of gradient vanishing/exploding problem, we propose a \textbf{Multi-Cell} architecture which gradually increases the depth of deep neural network and the resolution of input image, which both boosts the training time but also improves the classification accuracy. Further, considering the different stages of DR actually progress gradually, which means the labels of different stages are related. To considering the relationships of images with different stages, we propose a \textbf{Multi-Task} learning strategy which predicts the label with both classification and regression. Experimental results on the Kaggle dataset show that our method achieves a Kappa of 0.841 on test set which is the 4-th rank of all state-of-the-arts methods. Further, our Multi-Cell Multi-Task Convolutional Neural Networks (M$^2$CNN) solution is a general framework, which can be readily integrated with many other deep neural network architectures.

cs.CV↗

arXiv2018

Note on differential operators, CHY integrands, and unifying relations for amplitudes

An elegant unified web for amplitudes of various theories was given by Cachazo, He and Yuan in the CHY framework a few years ago. Recently, similar web has also been constructed by Cheung, Shen and Wen, which relies on a set of differential operators. In this note, by acting these differential operators on CHY-integrands systematically, we have established the relation between these two approaches. Thus, amplitudes for all theories which have CHY representations, include gravity theory, Einstein-Yang-Mills theory, Einstein-Maxwell theory, pure Yang-Mills theory, Yang-Mills-scalar theory, Born-Infeld theory, Dirac-Born-Infeld theory and its extension, bi-adjoint scalar theory, $ϕ^4$ theory, non-linear sigma model, as well as special Galileon theory, have been included in the unified web rooted from gravity theory.

hep-th↗

arXiv2017

Derivation of Feynman Rules for Higher Order Poles Using Cross-ratio Identities in CHY Construction

In order to generalize the integration rules to general CHY integrands which include higher order poles, algorithms are proposed in two directions. One is to conjecture new rules, and the other is to use the cross-ratio identity method. In this paper,we use the cross-ratio identity approach to re-derive the conjectured integration rules involving higher order poles for several special cases: the single double pole, single triple pole and duplex-double pole. The equivalence between the present formulas and the previously conjectured ones is discussed for the first two situations.

hep-th↗

arXiv2017

Analytic expressions of amplitudes by the cross-ratio identity method

In order to obtain the analytic expression of an amplitude from a generic CHY-integrand, a new algorithm based on the so-called cross-ratio identities has been proposed recently. In this paper, we apply this new approach to a variety of theories including: non-linear sigma model, special Galileon theory, pure Yang-Mills theory, pure gravity, Born-Infeld theory, Dirac-Born-Infeld theory and its extension, Yang-Mills-scalar theory, Einstein-Maxwell theory as well as Einstein-Yang-Mills theory. CHY-integrands of these theories which contain higher-order poles can be calculated conveniently by using the cross-ratio identity method, and all results above have been verified numerically.

hep-th↗

arXiv2016

The Q-cut Representation of One-loop Integrands and Unitarity Cut Method

Recently, a new construction for complete loop integrands of massless field theories has been proposed, with on-shell tree-level amplitudes delicately incorporated into its algorithm. This new approach reinterprets integrands in a novel form, namely the Q-cut representation. In this paper, by deriving one-loop integrands as examples, we elaborate in details the technique of this new representation, e.g., the summation over all possible Q-cuts as well as helicity states for the non-scalar internal particle in the loop. Moreover, we show that the integrand in the Q-cut representation naturally reduces to the integrand in the traditional unitarity cut method for each given cut channel, providing a cross-check for the new approach.

hep-th↗

arXiv2015

On Multi-step BCFW Recursion Relations

In this paper, we extensively investigate the new algorithm known as the multi-step BCFW recursion relations. Many interesting mathematical properties are found and understanding these aspects, one can find a systematic way to complete the calculation of amplitude after finite, definite steps and get the correct answer, without recourse to any specific knowledge from field theories, besides mass dimension and helicities. This process consists of the pole concentration and inconsistency elimination. Terms that survive inconsistency elimination cannot be determined by the new algorithm. They include polynomials and their generalizations, which turn out to be useful objects to be explored. Afterwards, we apply it to the Standard Model plus gravity to illustrate its power and limitation. Ensuring its workability, we also tentatively discuss how to improve its efficiency by reducing the steps.

hep-th↗