arXiv subjects

Jiang Liu

Publications and source records attributed to Jiang Liu.

At least 199 records · Page 11Linked to original sources

arXiv2020

Evaluation of Retinal Image Quality Assessment Networks in Different Color-spaces

Retinal image quality assessment (RIQA) is essential for controlling the quality of retinal imaging and guaranteeing the reliability of diagnoses by ophthalmologists or automated analysis systems. Existing RIQA methods focus on the RGB color-space and are developed based on small datasets with binary quality labels (i.e., `Accept' and `Reject'). In this paper, we first re-annotate an Eye-Quality (EyeQ) dataset with 28,792 retinal images from the EyePACS dataset, based on a three-level quality grading system (i.e., `Good', `Usable' and `Reject') for evaluating RIQA methods. Our RIQA dataset is characterized by its large-scale size, multi-level grading, and multi-modality. Then, we analyze the influences on RIQA of different color-spaces, and propose a simple yet efficient deep network, named Multiple Color-space Fusion Network (MCF-Net), which integrates the different color-space representations at both a feature-level and prediction-level to predict image quality grades. Experiments on our EyeQ dataset show that our MCF-Net obtains a state-of-the-art performance, outperforming the other deep learning methods. Furthermore, we also evaluate diabetic retinopathy (DR) detection methods on images of different quality, and demonstrate that the performances of automated diagnostic systems are highly dependent on image quality.

cs.CV↗

arXiv2020

Universal digital filtering for denoising volumetric retinal OCT and OCT angiography in 3D shearlet domain

Retinal optical coherence tomography (OCT) and OCT angiography (OCTA) suffer from the degeneration of image quality due to speckle noise and bulk-motion noise, respectively. Because the cross-sectional retina has distinct features in OCT and OCTA B-scans, existing digital filters that can denoise OCT efficiently are unable to handle the bulk-motion noise in OCTA. In this Letter, we propose a universal digital filtering approach that is capable of minimizing both types of noise. Considering the retinal capillaries in OCTA are hard to differentiate in B-scans while having distinct curvilinear structures in 3D volumes, we decompose the volumetric OCT and OCTA data with 3D shearlets thus efficiently separate the retinal tissue and vessels from the noise in this transform domain. Compared with wavelets and curvelets, the shearlets provide better representation of the layer edges in OCT and the vasculature in OCTA. Qualitative and quantitative results show the proposed method outperforms the state-of-the-art OCT and OCTA denoising methods. Besides, the superiority of 3D denoising is demonstrated by comparing the 3D shearlet filtering with its 2D counterpart.

eess.IV↗

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

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

Dense Dilated Network with Probability Regularized Walk for Vessel Detection

The detection of retinal vessel is of great importance in the diagnosis and treatment of many ocular diseases. Many methods have been proposed for vessel detection. However, most of the algorithms neglect the connectivity of the vessels, which plays an important role in the diagnosis. In this paper, we propose a novel method for retinal vessel detection. The proposed method includes a dense dilated network to get an initial detection of the vessels and a probability regularized walk algorithm to address the fracture issue in the initial detection. The dense dilated network integrates newly proposed dense dilated feature extraction blocks into an encoder-decoder structure to extract and accumulate features at different scales. A multiscale Dice loss function is adopted to train the network. To improve the connectivity of the segmented vessels, we also introduce a probability regularized walk algorithm to connect the broken vessels. The proposed method has been applied on three public data sets: DRIVE, STARE and CHASE_DB1. The results show that the proposed method outperforms the state-of-the-art methods in accuracy, sensitivity, specificity and also are under receiver operating characteristic curve.

eess.IV↗

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

Knowledge infused cascade convolutional neural network for segmenting retinal vessels in volumetric optical coherence tomography

We present a cascade deep neural network to segment retinal vessels in volumetric optical coherence tomography (OCT). Two types of knowledge are infused into the network for confining the searching regions. (1) Histology. The retinal vessels locate between the inner limiting membrane and the inner nuclear layer of human retina. (2) Imaging. The red blood cells inside the vessels scatter the OCT probe light forward and form projection shadows on the retinal pigment epithelium (RPE) layer, which is avascular thus perfect for localizing the retinal vessel in transverse plane. Qualitative and quantitative comparison results show that the proposed method outperforms the state-of-the-art deep learning and graph-based methods. This work demonstrates, instead of modifying the architectures of the deep networks, incorporating proper prior knowledge in the design of the image processing framework could be an efficient approach for handling such specific tasks.

eess.IV↗

arXiv2019

Deep learning enables extraction of capillary-level angiograms from single OCT volume

Optical coherence tomography angiography (OCTA) has drawn numerous attentions in ophthalmology. However, its data acquisition is time-consuming, because it is based on temporal-decorrelation principle thus requires multiple repeated volumetric OCT scans. In this paper, we developed a deep learning algorithm by combining a fovea attention mechanism with a residual neural network, which is able to extract capillary-level angiograms directly from a single OCT scan. The segmentation results of the inner limiting membrane and outer plexiform layers and the central $1\times1$ mm$^2$ field of view of the fovea are employed in the fovea attention mechanism. So the influences of large retinal vessels and choroidal vasculature on the extraction of capillaries can be minimized during the training of the network. The results demonstrate that the proposed algorithm has the capacity to better-visualizing capillaries around the foveal avascular zone than the existing work using a U-Net architecture.

physics.med-ph↗

arXiv2019

GetNet: Get Target Area for Image Pairing

Image pairing is an important research task in the field of computer vision. And finding image pairs containing objects of the same category is the basis of many tasks such as tracking and person re-identification, etc., and it is also the focus of our research. Existing traditional methods and deep learning-based methods have some degree of defects in speed or accuracy. In this paper, we made improvements on the Siamese network and proposed GetNet. The proposed method GetNet combines STN and Siamese network to get the target area first and then perform subsequent processing. Experiments show that our method achieves competitive results in speed and accuracy.

cs.CV↗

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

The Channel Attention based Context Encoder Network for Inner Limiting Membrane Detection

The optic disc segmentation is an important step for retinal image-based disease diagnosis such as glaucoma. The inner limiting membrane (ILM) is the first boundary in the OCT, which can help to extract the retinal pigment epithelium (RPE) through gradient edge information to locate the boundary of the optic disc. Thus, the ILM layer segmentation is of great importance for optic disc localization. In this paper, we build a new optic disc centered dataset from 20 volunteers and manually annotated the ILM boundary in each OCT scan as ground-truth. We also propose a channel attention based context encoder network modified from the CE-Net to segment the optic disc. It mainly contains three phases: the encoder module, the channel attention based context encoder module, and the decoder module. Finally, we demonstrate that our proposed method achieves state-of-the-art disc segmentation performance on our dataset mentioned above.

eess.IV↗

arXiv2019

SkrGAN: Sketching-rendering Unconditional Generative Adversarial Networks for Medical Image Synthesis

Generative Adversarial Networks (GANs) have the capability of synthesizing images, which have been successfully applied to medical image synthesis tasks. However, most of existing methods merely consider the global contextual information and ignore the fine foreground structures, e.g., vessel, skeleton, which may contain diagnostic indicators for medical image analysis. Inspired by human painting procedure, which is composed of stroking and color rendering steps, we propose a Sketching-rendering Unconditional Generative Adversarial Network (SkrGAN) to introduce a sketch prior constraint to guide the medical image generation. In our SkrGAN, a sketch guidance module is utilized to generate a high quality structural sketch from random noise, then a color render mapping is used to embed the sketch-based representations and resemble the background appearances. Experimental results show that the proposed SkrGAN achieves the state-of-the-art results in synthesizing images for various image modalities, including retinal color fundus, X-Ray, Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). In addition, we also show that the performances of medical image segmentation method have been improved by using our synthesized images as data augmentation.

cs.CV↗

arXiv2019

Identifying the magnetospheric driver of STEVE

For the first time, we identify the magnetospheric driver of STEVE, east-west aligned narrow emissions in the subauroral region. In the ionosphere, STEVE is associated with subauroral ion drift (SAID) features of high electron temperature peak, density gradient, and strong westward ion flow. In this study, we present STEVE's magnetospheric driver region at a sharp plasmapause containing: strong tailward quasi-static electric field, kinetic Alfven waves, parallel electron acceleration, perpendicular ion drift. The observed continuous emissions of STEVE are possibly caused by ionospheric electron heating due to heat conduction and/or auroral acceleration process powered by Alfven waves, both driven by the observed equatorial magnetospheric processes. The observed green emissions are likely optical manifestations of electron precipitations associated with wave structures traveling along the plasmapause. The observed SAR arc at lower latitudes likely corresponds to the formation of low-energy plasma inside the plasmapause by Coulomb collisions between ring current ions and plasmaspheric plasma.

physics.space-ph↗

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↗

arXiv2019

Angle-Closure Detection in Anterior Segment OCT based on Multi-Level Deep Network

Irreversible visual impairment is often caused by primary angle-closure glaucoma, which could be detected via Anterior Segment Optical Coherence Tomography (AS-OCT). In this paper, an automated system based on deep learning is presented for angle-closure detection in AS-OCT images. Our system learns a discriminative representation from training data that captures subtle visual cues not modeled by handcrafted features. A Multi-Level Deep Network (MLDN) is proposed to formulate this learning, which utilizes three particular AS-OCT regions based on clinical priors: the global anterior segment structure, local iris region, and anterior chamber angle (ACA) patch. In our method, a sliding window based detector is designed to localize the ACA region, which addresses ACA detection as a regression task. Then, three parallel sub-networks are applied to extract AS-OCT representations for the global image and at clinically-relevant local regions. Finally, the extracted deep features of these sub-networks are concatenated into one fully connected layer to predict the angle-closure detection result. In the experiments, our system is shown to surpass previous detection methods and other deep learning systems on two clinical AS-OCT datasets.

cs.CV↗

arXiv2019

3D Magnetic Reconnection with a spatially confined X-line extent -- Implications for Dipolarizing Flux Bundles and the Dawn-Dusk Asymmetry

Using 3D particle-in-cell (PIC) simulations, we study magnetic reconnection with the x-line being spatially confined in the current direction. We include thick current layers to prevent reconnection at two ends of a thin current sheet that has a thickness on an ion inertial (di) scale. The reconnection rate and outflow speed drop significantly when the extent of the thin current sheet in the current direction is < O(10 di). When the thin current sheet extent is long enough, we find it consists of two distinct regions; an inactive region (on the ion-drifting side) exists adjacent to the active region where reconnection proceeds normally as in a 2D case. The extent of this inactive region is ~ O(10 di), and it suppresses reconnection when the thin current sheet extent is comparable or shorter. The time-scale of current sheet thinning toward fast reconnection can be translated into the spatial-scale of this inactive region; because electron drifts inside the ion diffusion region transport the reconnected magnetic flux, that drives outflows and furthers the current sheet thinning, away from this region. This is a consequence of the Hall effect in 3D. While this inactive region may explain the shortest possible azimuthal extent of dipolarizing flux bundles at Earth, it may also explain the dawn-dusk asymmetry observed at the magnetotail of Mercury, that has a global dawn-dusk extent much shorter than that of Earth.

physics.plasm-ph↗

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↗