arXiv subjects

Jiang Liu

Publications and source records attributed to Jiang Liu.

At least 181 records · Page 10Linked to original sources

arXiv2020

Attention-based Saliency Hashing for Ophthalmic Image Retrieval

Deep hashing methods have been proved to be effective for the large-scale medical image search assisting reference-based diagnosis for clinicians. However, when the salient region plays a maximal discriminative role in ophthalmic image, existing deep hashing methods do not fully exploit the learning ability of the deep network to capture the features of salient regions pointedly. The different grades or classes of ophthalmic images may be share similar overall performance but have subtle differences that can be differentiated by mining salient regions. To address this issue, we propose a novel end-to-end network, named Attention-based Saliency Hashing (ASH), for learning compact hash-code to represent ophthalmic images. ASH embeds a spatial-attention module to focus more on the representation of salient regions and highlights their essential role in differentiating ophthalmic images. Benefiting from the spatial-attention module, the information of salient regions can be mapped into the hash-code for similarity calculation. In the training stage, we input the image pairs to share the weights of the network, and a pairwise loss is designed to maximize the discriminability of the hash-code. In the retrieval stage, ASH obtains the hash-code by inputting an image with an end-to-end manner, then the hash-code is used to similarity calculation to return the most similar images. Extensive experiments on two different modalities of ophthalmic image datasets demonstrate that the proposed ASH can further improve the retrieval performance compared to the state-of-the-art deep hashing methods due to the huge contributions of the spatial-attention module.

cs.CV↗

arXiv2020

Probabilistic Latent Factor Model for Collaborative Filtering with Bayesian Inference

Latent Factor Model (LFM) is one of the most successful methods for Collaborative filtering (CF) in the recommendation system, in which both users and items are projected into a joint latent factor space. Base on matrix factorization applied usually in pattern recognition, LFM models user-item interactions as inner products of factor vectors of user and item in that space and can be efficiently solved by least square methods with optimal estimation. However, such optimal estimation methods are prone to overfitting due to the extreme sparsity of user-item interactions. In this paper, we propose a Bayesian treatment for LFM, named Bayesian Latent Factor Model (BLFM). Based on observed user-item interactions, we build a probabilistic factor model in which the regularization is introduced via placing prior constraint on latent factors, and the likelihood function is established over observations and parameters. Then we draw samples of latent factors from the posterior distribution with Variational Inference (VI) to predict expected value. We further make an extension to BLFM, called BLFMBias, incorporating user-dependent and item-dependent biases into the model for enhancing performance. Extensive experiments on the movie rating dataset show the effectiveness of our proposed models by compared with several strong baselines.

cs.IR↗

arXiv2020

Calibrated Intervention and Containment of the COVID-19 Pandemic

Within a short period of time, COVID-19 grew into a world-wide pandemic. Transmission by pre-symptomatic and asymptomatic viral carriers rendered intervention and containment of the disease extremely challenging. Based on reported infection case studies, we construct an epidemiological model that focuses on transmission around the symptom onset. The model is calibrated against incubation period and pairwise transmission statistics during the initial outbreaks of the pandemic outside Wuhan with minimal non-pharmaceutical interventions. Mathematical treatment of the model yields explicit expressions for the size of latent and pre-symptomatic subpopulations during the exponential growth phase, with the local epidemic growth rate as input. We then explore reduction of the basic reproduction number R_0 through specific disease control measures such as contact tracing, testing, social distancing, wearing masks and sheltering in place. When these measures are implemented in combination, their effects on R_0 multiply. We also compare our model behaviour to the first wave of the COVID-19 spreading in various affected regions and highlight generic and less generic features of the pandemic development.

q-bio.PE↗

arXiv2020

CS2-Net: Deep Learning Segmentation of Curvilinear Structures in Medical Imaging

Automated detection of curvilinear structures, e.g., blood vessels or nerve fibres, from medical and biomedical images is a crucial early step in automatic image interpretation associated to the management of many diseases. Precise measurement of the morphological changes of these curvilinear organ structures informs clinicians for understanding the mechanism, diagnosis, and treatment of e.g. cardiovascular, kidney, eye, lung, and neurological conditions. In this work, we propose a generic and unified convolution neural network for the segmentation of curvilinear structures and illustrate in several 2D/3D medical imaging modalities. We introduce a new curvilinear structure segmentation network (CS2-Net), which includes a self-attention mechanism in the encoder and decoder to learn rich hierarchical representations of curvilinear structures. Two types of attention modules - spatial attention and channel attention - are utilized to enhance the inter-class discrimination and intra-class responsiveness, to further integrate local features with their global dependencies and normalization, adaptively. Furthermore, to facilitate the segmentation of curvilinear structures in medical images, we employ a 1x3 and a 3x1 convolutional kernel to capture boundary features. ...

eess.IV↗

arXiv2020

An Optimum Algorithm for Quantum Search

This paper discusses an improvement to Grover's algorithm for searches where target states are Hamming weight eigenstates and search space is not ordered. It is shown that under these conditions search efficiency depends on the smaller number of 0's and 1's, not the total length, of binary string of target state, and that Grover's algorithm can be improved whenever number of 0's and number 1's are not equal. In particular, improvement can be exponential when number of 0's or number of 1's is very small relative to binary string length. One interesting application is that Dicke state preparation, which in Grover's algorithm is P on average, can be made poly-efficient in all cases. For decision making process, this improvement won't improve computation efficiency, but can make implementation much simpler.

quant-ph↗

arXiv2020

The Geometric Unscented Kalman Filter

Many filters have been proposed in recent decades for the nonlinear state estimation problem. The linearization-based extended Kalman filter (EKF) is widely applied to nonlinear industrial systems. As EKF is limited in accuracy and reliability, sequential Monte-Carlo methods or particle filters (PF) can obtain superior accuracy at the cost of a huge number of random samples. The unscented Kalman filter (UKF) can achieve adequate accuracy more efficiently by using deterministic samples, but its weights may be negative, which might cause instability problem. For Gaussian filters, the cubature Kalman filter (CKF) and Gauss Hermit filter (GHF) employ cubature and respectively Gauss-Hermite rules to approximate statistic information of random variables and exhibit impressive performances in practical problems. Inspired by this work, this paper presents a new nonlinear estimation scheme named after geometric unscented Kalman filter (GUF). The GUF chooses the filtering framework of CKF for updating data and develops a geometric unscented sampling (GUS) strategy for approximating random variables. The main feature of GUS is selecting uniformly distributed samples according to the probability and geometric location similar to UKF and CKF, and having positive weights like PF. Through such way, GUF can maintain adequate accuracy as GHF with reasonable efficiency and good stability. The GUF does not suffer from the exponential increase of sample size as for PF or failure to converge resulted from non-positive weights as for high order CKF and UKF.

eess.SY↗

arXiv2020

Automatic Segmentation and Visualization of Choroid in OCT with Knowledge Infused Deep Learning

The choroid provides oxygen and nourishment to the outer retina thus is related to the pathology of various ocular diseases. Optical coherence tomography (OCT) is advantageous in visualizing and quantifying the choroid in vivo. (1) The lower boundary of the choroid (choroid-sclera interface) in OCT is fuzzy, which makes the automatic segmentation difficult and inaccurate. (2) The visualization of the choroid is hindered by the vessel shadows from the superficial layers of the inner retina. In this paper, we propose to incorporate medical and imaging prior knowledge with deep learning to address these two problems. We propose a biomarker infused global-to-local network for the choroid segmentation. It leverages the choroidal thickness, a primary biomarker in clinic, as a constraint to improve the segmentation accuracy. We also design a global-to-local strategy in the choroid segmentation: a global module is used to segment all the retinal and choroidal layers simultaneously for suppressing overfitting and providing global structure information, then a local module is used to refine the segmentation with the biomarker infusion. To eliminate the retinal vessel shadows, we propose a pipeline that firstly use anatomical and OCT imaging knowledge to locate the shadows using their projection on the retinal pigment epithelium layer, then the contents of the choroidal vasculature at the shadow locations are predicted with an edge-to-texture generative adversarial inpainting network. The experiments show our method outperforms the existing methods on both the segmentation and shadow elimination tasks. We further apply the proposed method in a clinical prospective study for understanding the pathology of glaucoma by detecting the structure and vascular changes of the choroid related to the elevation of intra-ocular pressure.

eess.IV↗

arXiv2020

Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images

Anomaly detection in retinal image refers to the identification of abnormality caused by various retinal diseases/lesions, by only leveraging normal images in training phase. Normal images from healthy subjects often have regular structures (e.g., the structured blood vessels in the fundus image, or structured anatomy in optical coherence tomography image). On the contrary, the diseases and lesions often destroy these structures. Motivated by this, we propose to leverage the relation between the image texture and structure to design a deep neural network for anomaly detection. Specifically, we first extract the structure of the retinal images, then we combine both the structure features and the last layer features extracted from original health image to reconstruct the original input healthy image. The image feature provides the texture information and guarantees the uniqueness of the image recovered from the structure. In the end, we further utilize the reconstructed image to extract the structure and measure the difference between structure extracted from original and the reconstructed image. On the one hand, minimizing the reconstruction difference behaves like a regularizer to guarantee that the image is corrected reconstructed. On the other hand, such structure difference can also be used as a metric for normality measurement. The whole network is termed as P-Net because it has a ``P'' shape. Extensive experiments on RESC dataset and iSee dataset validate the effectiveness of our approach for anomaly detection in retinal images. Further, our method also generalizes well to novel class discovery in retinal images and anomaly detection in real-world images.

eess.IV↗

arXiv2020

AGE Challenge: Angle Closure Glaucoma Evaluation in Anterior Segment Optical Coherence Tomography

Angle closure glaucoma (ACG) is a more aggressive disease than open-angle glaucoma, where the abnormal anatomical structures of the anterior chamber angle (ACA) may cause an elevated intraocular pressure and gradually lead to glaucomatous optic neuropathy and eventually to visual impairment and blindness. Anterior Segment Optical Coherence Tomography (AS-OCT) imaging provides a fast and contactless way to discriminate angle closure from open angle. Although many medical image analysis algorithms have been developed for glaucoma diagnosis, only a few studies have focused on AS-OCT imaging. In particular, there is no public AS-OCT dataset available for evaluating the existing methods in a uniform way, which limits progress in the development of automated techniques for angle closure detection and assessment. To address this, we organized the Angle closure Glaucoma Evaluation challenge (AGE), held in conjunction with MICCAI 2019. The AGE challenge consisted of two tasks: scleral spur localization and angle closure classification. For this challenge, we released a large dataset of 4800 annotated AS-OCT images from 199 patients, and also proposed an evaluation framework to benchmark and compare different models. During the AGE challenge, over 200 teams registered online, and more than 1100 results were submitted for online evaluation. Finally, eight teams participated in the onsite challenge. In this paper, we summarize these eight onsite challenge methods and analyze their corresponding results for the two tasks. We further discuss limitations and future directions. In the AGE challenge, the top-performing approach had an average Euclidean Distance of 10 pixels (10um) in scleral spur localization, while in the task of angle closure classification, all the algorithms achieved satisfactory performances, with two best obtaining an accuracy rate of 100%.

cs.CV↗

arXiv2020

Reconstruction and Quantification of 3D Iris Surface for Angle-Closure Glaucoma Detection in Anterior Segment OCT

Precise characterization and analysis of iris shape from Anterior Segment OCT (AS-OCT) are of great importance in facilitating diagnosis of angle-closure-related diseases. Existing methods focus solely on analyzing structural properties identified from the 2D slice, while accurate characterization of morphological changes of iris shape in 3D AS-OCT may be able to reveal in addition the risk of disease progression. In this paper, we propose a novel framework for reconstruction and quantification of 3D iris surface from AS-OCT imagery. We consider it to be the first work to detect angle-closure glaucoma by means of 3D representation. An iris segmentation network with wavelet refinement block (WRB) is first proposed to generate the initial shape of the iris from single AS-OCT slice. The 3D iris surface is then reconstructed using a guided optimization method with Poisson-disk sampling. Finally, a set of surface-based features are extracted, which are used in detecting of angle-closure glaucoma. Experimental results demonstrate that our method is highly effective in iris segmentation and surface reconstruction. Moreover, we show that 3D-based representation achieves better performance in angle-closure glaucoma detection than does 2D-based feature.

eess.IV↗

arXiv2020

Open-Narrow-Synechiae Anterior Chamber Angle Classification in AS-OCT Sequences

Anterior chamber angle (ACA) classification is a key step in the diagnosis of angle-closure glaucoma in Anterior Segment Optical Coherence Tomography (AS-OCT). Existing automated analysis methods focus on a binary classification system (i.e., open angle or angle-closure) in a 2D AS-OCT slice. However, clinical diagnosis requires a more discriminating ACA three-class system (i.e., open, narrow, or synechiae angles) for the benefit of clinicians who seek better to understand the progression of the spectrum of angle-closure glaucoma types. To address this, we propose a novel sequence multi-scale aggregation deep network (SMA-Net) for open-narrow-synechiae ACA classification based on an AS-OCT sequence. In our method, a Multi-Scale Discriminative Aggregation (MSDA) block is utilized to learn the multi-scale representations at slice level, while a ConvLSTM is introduced to study the temporal dynamics of these representations at sequence level. Finally, a multi-level loss function is used to combine the slice-based and sequence-based losses. The proposed method is evaluated across two AS-OCT datasets. The experimental results show that the proposed method outperforms existing state-of-the-art methods in applicability, effectiveness, and accuracy. We believe this work to be the first attempt to classify ACAs into open, narrow, or synechia types grading using AS-OCT sequences.

cs.CV↗

arXiv2020

An Optimization Approach to Jacobian Conjecture

Let $n\geq 2$ and $\mathbb K $ be a number field of characteristic $0$. Jacobian Conjecture asserts for a polynomial map $\mathcal P$ from $\mathbb K ^n$ to itself, if the determinant of its Jacobian matrix is a nonzero constant in $\mathbb K $ then the inverse $\mathcal P^{-1}$ exists and is also a polynomial map. This conjecture was firstly proposed by Keller in 1939 for $\mathbb K ^n=\mathbb C^2$ and put in Smale's 1998 list of Mathematical Problems for the Next Century. This study is going to present a proof for the conjecture. Our proof is based on Dru{ż}kowski Map and Hadamard's Diffeomorphism Theorem, and additionally uses some optimization idea.

math.GM↗

arXiv2020

Beamforming Through Reconfigurable Intelligent Surfaces in Single-User MIMO Systems: SNR Distribution and Scaling Laws in the Presence of Channel Fading and Phase Noise

We consider a fading channel in which a multi-antenna transmitter communicates with a multi-antenna receiver through a reconfigurable intelligent surface (RIS) that is made of $N$ reconfigurable passive scatterers impaired by phase noise. The beamforming vector at the transmitter, the combining vector at the receiver, and the phase shifts of the $N$ scatterers are optimized in order to maximize the signal-to-noise-ratio (SNR) at the receiver. By assuming Rayleigh fading (or line-of-sight propagation) on the transmitter-RIS link and Rayleigh fading on the RIS-receiver link, we prove that the SNR is a random variable that is equivalent in distribution to the product of three (or two) independent random variables whose distributions are approximated by two (or one) gamma random variables and the sum of two scaled non-central chi-square random variables. The proposed analytical framework allows us to quantify the robustness of RIS-aided transmission to fading channels. For example, we prove that the amount of fading experienced on the transmitter-RIS-receiver channel linearly decreases with $N$. This proves that RISs of large size can be effectively employed to make fading less severe and wireless channels more reliable.

cs.IT↗

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

Lossless Attention in Convolutional Networks for Facial Expression Recognition in the Wild

Unlike the constraint frontal face condition, faces in the wild have various unconstrained interference factors, such as complex illumination, changing perspective and various occlusions. Facial expressions recognition (FER) in the wild is a challenging task and existing methods can't perform well. However, for occluded faces (containing occlusion caused by other objects and self-occlusion caused by head posture changes), the attention mechanism has the ability to focus on the non-occluded regions automatically. In this paper, we propose a Lossless Attention Model (LLAM) for convolutional neural networks (CNN) to extract attention-aware features from faces. Our module avoids decay information in the process of generating attention maps by using the information of the previous layer and not reducing the dimensionality. Sequentially, we adaptively refine the feature responses by fusing the attention map with the feature map. We participate in the seven basic expression classification sub-challenges of FG-2020 Affective Behavior Analysis in-the-wild Challenge. And we validate our method on the Aff-Wild2 datasets released by the Challenge. The total accuracy (Accuracy) and the unweighted mean (F1) of our method on the validation set are 0.49 and 0.38 respectively, and the final result is 0.42 (0.67 F1-Score + 0.33 Accuracy).

cs.CV↗

arXiv2020

A Classical $π$ Machine and Grover's Algorithm

This paper studies a well-known $π$ machine illustrated by Fig.(1). It is shown that the $π$ machine can compute digits of $π$ if the ratio of block weights, $m_2/m_1$, satisfies certain conditions, and that dynamics of the $π$ machine is identical to that of Grover's algorithm [1] in quantum computing.

quant-ph↗

arXiv2020

A Two-Stream Meticulous Processing Network for Retinal Vessel Segmentation

Vessel segmentation in fundus is a key diagnostic capability in ophthalmology, and there are various challenges remained in this essential task. Early approaches indicate that it is often difficult to obtain desirable segmentation performance on thin vessels and boundary areas due to the imbalance of vessel pixels with different thickness levels. In this paper, we propose a novel two-stream Meticulous-Processing Network (MP-Net) for tackling this problem. To pay more attention to the thin vessels and boundary areas, we firstly propose an efficient hierarchical model automatically stratifies the ground-truth masks into different thickness levels. Then a novel two-stream adversarial network is introduced to use the stratification results with a balanced loss function and an integration operation to achieve a better performance, especially in thin vessels and boundary areas detecting. Our model is proved to outperform state-of-the-art methods on DRIVE, STARE, and CHASE_DB1 datasets.

cs.CV↗