arXiv subjects

Lin Yang

Publications and source records attributed to Lin Yang.

At least 235 records · Page 13Linked to original sources

arXiv2019

Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition

The goal of MRI reconstruction is to restore a high fidelity image from partially observed measurements. This partial view naturally induces reconstruction uncertainty that can only be reduced by acquiring additional measurements. In this paper, we present a novel method for MRI reconstruction that, at inference time, dynamically selects the measurements to take and iteratively refines the prediction in order to best reduce the reconstruction error and, thus, its uncertainty. We validate our method on a large scale knee MRI dataset, as well as on ImageNet. Results show that (1) our system successfully outperforms active acquisition baselines; (2) our uncertainty estimates correlate with error maps; and (3) our ResNet-based architecture surpasses standard pixel-to-pixel models in the task of MRI reconstruction. The proposed method not only shows high-quality reconstructions but also paves the road towards more applicable solutions for accelerating MRI.

cs.CV↗

arXiv2019

Cascade Decoder: A Universal Decoding Method for Biomedical Image Segmentation

The Encoder-Decoder architecture is a main stream deep learning model for biomedical image segmentation. The encoder fully compresses the input and generates encoded features, and the decoder then produces dense predictions using encoded features. However, decoders are still under-explored in such architectures. In this paper, we comprehensively study the state-of-the-art Encoder-Decoder architectures, and propose a new universal decoder, called cascade decoder, to improve semantic segmentation accuracy. Our cascade decoder can be embedded into existing networks and trained altogether in an end-to-end fashion. The cascade decoder structure aims to conduct more effective decoding of hierarchically encoded features and is more compatible with common encoders than the known decoders. We replace the decoders of state-of-the-art models with our cascade decoder for several challenging biomedical image segmentation tasks, and the considerable improvements achieved demonstrate the efficacy of our new decoding method.

cs.CV↗

arXiv2019

Online Inventory Management with Application to Energy Procurement in Data Centers

Motivated by the application of energy storage management in electricity markets, this paper considers the problem of online linear programming with inventory management constraints. Specifically, a decision maker should satisfy some units of an asset as her demand, either form a market with time-varying price or from her own inventory. The decision maker is presented a price in slot-by-slot manner, and must immediately decide the purchased amount with the current price to cover the demand or to store in inventory for covering the future demand. The inventory has a limited capacity and its critical role is to buy and store assets at low price and use the stored assets to cover the demand at high price. The ultimate goal of the decision maker is to cover the demands while minimizing the cost of buying assets from the market. We propose BatMan, an online algorithm for simple inventory models, and BatManRate, an extended version for the case with rate constraints. Both BatMan and BatManRate achieve optimal competitive ratios, meaning that no other online algorithm can achieve a better theoretical guarantee. To illustrate the results, we use the proposed algorithms to design and evaluate energy procurement and storage management strategies for data centers with a portfolio of energy sources including the electric grid, local renewable generation, and energy storage systems.

cs.DS↗

arXiv2019

Physical Folding Codes for Proteins

Exploring and understanding the protein-folding problem has been a long-standing challenge in molecular biology. Here, using molecular dynamics simulation, we reveal how parallel distributed adjacent planar peptide groups of unfolded proteins fold reproducibly following explicit physical folding codes in aqueous environments due to electrostatic attractions. Superfast folding of protein is found to be powered by the contribution of the formation of hydrogen bonds. Temperature-induced torsional waves propagating along unfolded proteins break the parallel distributed state of specific amino acids, inferred as the beginning of folding. Electric charge and rotational resistance differences among neighboring side-chains are used to decipher the physical folding codes by means of which precise secondary structures develop. We present a powerful method of decoding amino acid sequences to predict native structures of proteins. The method is verified by comparing the results available from experiments in the literature.

q-bio.BM↗

arXiv2018

A New Ensemble Learning Framework for 3D Biomedical Image Segmentation

3D image segmentation plays an important role in biomedical image analysis. Many 2D and 3D deep learning models have achieved state-of-the-art segmentation performance on 3D biomedical image datasets. Yet, 2D and 3D models have their own strengths and weaknesses, and by unifying them together, one may be able to achieve more accurate results. In this paper, we propose a new ensemble learning framework for 3D biomedical image segmentation that combines the merits of 2D and 3D models. First, we develop a fully convolutional network based meta-learner to learn how to improve the results from 2D and 3D models (base-learners). Then, to minimize over-fitting for our sophisticated meta-learner, we devise a new training method that uses the results of the base-learners as multiple versions of "ground truths". Furthermore, since our new meta-learner training scheme does not depend on manual annotation, it can utilize abundant unlabeled 3D image data to further improve the model. Extensive experiments on two public datasets (the HVSMR 2016 Challenge dataset and the mouse piriform cortex dataset) show that our approach is effective under fully-supervised, semi-supervised, and transductive settings, and attains superior performance over state-of-the-art image segmentation methods.

cs.CV↗

arXiv2018

A Scalable Optimization Mechanism for Pairwise based Discrete Hashing

Maintaining the pair similarity relationship among originally high-dimensional data into a low-dimensional binary space is a popular strategy to learn binary codes. One simiple and intutive method is to utilize two identical code matrices produced by hash functions to approximate a pairwise real label matrix. However, the resulting quartic problem is difficult to directly solve due to the non-convex and non-smooth nature of the objective. In this paper, unlike previous optimization methods using various relaxation strategies, we aim to directly solve the original quartic problem using a novel alternative optimization mechanism to linearize the quartic problem by introducing a linear regression model. Additionally, we find that gradually learning each batch of binary codes in a sequential mode, i.e. batch by batch, is greatly beneficial to the convergence of binary code learning. Based on this significant discovery and the proposed strategy, we introduce a scalable symmetric discrete hashing algorithm that gradually and smoothly updates each batch of binary codes. To further improve the smoothness, we also propose a greedy symmetric discrete hashing algorithm to update each bit of batch binary codes. Moreover, we extend the proposed optimization mechanism to solve the non-convex optimization problems for binary code learning in many other pairwise based hashing algorithms. Extensive experiments on benchmark single-label and multi-label databases demonstrate the superior performance of the proposed mechanism over recent state-of-the-art methods.

cs.IR↗

arXiv2018

Super Characters: A Conversion from Sentiment Classification to Image Classification

We propose a method named Super Characters for sentiment classification. This method converts the sentiment classification problem into image classification problem by projecting texts into images and then applying CNN models for classification. Text features are extracted automatically from the generated Super Characters images, hence there is no need of any explicit step of embedding the words or characters into numerical vector representations. Experimental results on large social media corpus show that the Super Characters method consistently outperforms other methods for sentiment classification and topic classification tasks on ten large social media datasets of millions of contents in four different languages, including Chinese, Japanese, Korean and English.

cs.CL↗

arXiv2018

Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization

Stochastic optimization naturally arises in machine learning. Efficient algorithms with provable guarantees, however, are still largely missing, when the objective function is nonconvex and the data points are dependent. This paper studies this fundamental challenge through a streaming PCA problem for stationary time series data. Specifically, our goal is to estimate the principle component of time series data with respect to the covariance matrix of the stationary distribution. Computationally, we propose a variant of Oja's algorithm combined with downsampling to control the bias of the stochastic gradient caused by the data dependency. Theoretically, we quantify the uncertainty of our proposed stochastic algorithm based on diffusion approximations. This allows us to prove the asymptotic rate of convergence and further implies near optimal asymptotic sample complexity. Numerical experiments are provided to support our analysis.

cs.LG↗

arXiv2018

ConvPath: A Software Tool for Lung Adenocarcinoma Digital Pathological Image Analysis Aided by Convolutional Neural Network

The spatial distributions of different types of cells could reveal a cancer cell growth pattern, its relationships with the tumor microenvironment and the immune response of the body, all of which represent key hallmarks of cancer. However, manually recognizing and localizing all the cells in pathology slides are almost impossible. In this study, we developed an automated cell type classification pipeline, ConvPath, which includes nuclei segmentation, convolutional neural network-based tumor, stromal and lymphocytes classification, and extraction of tumor microenvironment related features for lung cancer pathology images. The overall classification accuracy is 92.9% and 90.1% in training and independent testing datasets, respectively. By identifying cells and classifying cell types, this pipeline can convert a pathology image into a spatial map of tumor, stromal and lymphocyte cells. From this spatial map, we can extracted features that characterize the tumor micro-environment. Based on these features, we developed an image feature-based prognostic model and validated the model in two independent cohorts. The predicted risk group serves as an independent prognostic factor, after adjusting for clinical variables that include age, gender, smoking status, and stage.

cs.CV↗

arXiv2018

CT Image Enhancement Using Stacked Generative Adversarial Networks and Transfer Learning for Lesion Segmentation Improvement

Automated lesion segmentation from computed tomography (CT) is an important and challenging task in medical image analysis. While many advancements have been made, there is room for continued improvements. One hurdle is that CT images can exhibit high noise and low contrast, particularly in lower dosages. To address this, we focus on a preprocessing method for CT images that uses stacked generative adversarial networks (SGAN) approach. The first GAN reduces the noise in the CT image and the second GAN generates a higher resolution image with enhanced boundaries and high contrast. To make up for the absence of high quality CT images, we detail how to synthesize a large number of low- and high-quality natural images and use transfer learning with progressively larger amounts of CT images. We apply both the classic GrabCut method and the modern holistically nested network (HNN) to lesion segmentation, testing whether SGAN can yield improved lesion segmentation. Experimental results on the DeepLesion dataset demonstrate that the SGAN enhancements alone can push GrabCut performance over HNN trained on original images. We also demonstrate that HNN + SGAN performs best compared against four other enhancement methods, including when using only a single GAN.

cs.CV↗

arXiv2018

Iterative Attention Mining for Weakly Supervised Thoracic Disease Pattern Localization in Chest X-Rays

Given image labels as the only supervisory signal, we focus on harvesting, or mining, thoracic disease localizations from chest X-ray images. Harvesting such localizations from existing datasets allows for the creation of improved data sources for computer-aided diagnosis and retrospective analyses. We train a convolutional neural network (CNN) for image classification and propose an attention mining (AM) strategy to improve the model's sensitivity or saliency to disease patterns. The intuition of AM is that once the most salient disease area is blocked or hidden from the CNN model, it will pay attention to alternative image regions, while still attempting to make correct predictions. However, the model requires to be properly constrained during AM, otherwise, it may overfit to uncorrelated image parts and forget the valuable knowledge that it has learned from the original image classification task. To alleviate such side effects, we then design a knowledge preservation (KP) loss, which minimizes the discrepancy between responses for X-ray images from the original and the updated networks. Furthermore, we modify the CNN model to include multi-scale aggregation (MSA), improving its localization ability on small-scale disease findings, e.g., lung nodules. We experimentally validate our method on the publicly-available ChestX-ray14 dataset, outperforming a class activation map (CAM)-based approach, and demonstrating the value of our novel framework for mining disease locations.

cs.CV↗

arXiv2018

Accurate Weakly-Supervised Deep Lesion Segmentation using Large-Scale Clinical Annotations: Slice-Propagated 3D Mask Generation from 2D RECIST

Volumetric lesion segmentation from computed tomography (CT) images is a powerful means to precisely assess multiple time-point lesion/tumor changes. However, because manual 3D segmentation is prohibitively time consuming, current practices rely on an imprecise surrogate called response evaluation criteria in solid tumors (RECIST). Despite their coarseness, RECIST markers are commonly found in current hospital picture and archiving systems (PACS), meaning they can provide a potentially powerful, yet extraordinarily challenging, source of weak supervision for full 3D segmentation. Toward this end, we introduce a convolutional neural network (CNN) based weakly supervised slice-propagated segmentation (WSSS) method to 1) generate the initial lesion segmentation on the axial RECIST-slice; 2) learn the data distribution on RECIST-slices; 3) extrapolate to segment the whole lesion slice by slice to finally obtain a volumetric segmentation. To validate the proposed method, we first test its performance on a fully annotated lymph node dataset, where WSSS performs comparably to its fully supervised counterparts. We then test on a comprehensive lesion dataset with 32,735 RECIST marks, where we report a mean Dice score of 92% on RECIST-marked slices and 76% on the entire 3D volumes.

cs.CV↗

arXiv2018

Deep Learning Based Instance Segmentation in 3D Biomedical Images Using Weak Annotation

Instance segmentation in 3D images is a fundamental task in biomedical image analysis. While deep learning models often work well for 2D instance segmentation, 3D instance segmentation still faces critical challenges, such as insufficient training data due to various annotation difficulties in 3D biomedical images. Common 3D annotation methods (e.g., full voxel annotation) incur high workloads and costs for labeling enough instances for training deep learning 3D instance segmentation models. In this paper, we propose a new weak annotation approach for training a fast deep learning 3D instance segmentation model without using full voxel mask annotation. Our approach needs only 3D bounding boxes for all instances and full voxel annotation for a small fraction of the instances, and uses a novel two-stage 3D instance segmentation model utilizing these two kinds of annotation, respectively. We evaluate our approach on several biomedical image datasets, and the experimental results show that (1) with full annotated boxes and a small amount of masks, our approach can achieve similar performance as the best known methods using full annotation, and (2) with similar annotation time, our approach outperforms the best known methods that use full annotation.

cs.CV↗

arXiv2018

Tunable disorder and localization in the rare-earth nickelates

The rare-earth nickelates are a rich playground for transport properties, known to host non-Fermi liquid character, resistance saturation and metal-insulator transitions. We report a study of transport in LaNiO3 in the presence of tunable disorder induced by irradiation. While pristine LaNiO3 samples are metallic, highly irradiated samples show insulating behaviour at all temperatures. Using irradiation fluence as a tuning handle, we uncover an intermediate region hosting a metal-insulator transition. This transition falls within the Mott-Ioffe-Regel regime wherein the mean free path is comparable to lattice spacing. In the high temperature metallic regime, we find a transition from non-Fermi liquid to a Fermi-liquid-like character. On the insulating side of the metal-insulator transition, we find behaviour that is consistent with weak localization. This is reflected in magnetoresistance that scales with the square of the field and in resistivity. In the highly irradiated insulating samples, we find good agreement with variable range hopping, consistent with Anderson localization. We find qualitatively similar behaviour in thick PrNiO3 films as well. Our results demonstrate that ion irradiation can be used to tailor transport, serving as an excellent tool to study the physics of localization.

cond-mat.mtrl-sci↗

arXiv2018

BoxNet: Deep Learning Based Biomedical Image Segmentation Using Boxes Only Annotation

In recent years, deep learning (DL) methods have become powerful tools for biomedical image segmentation. However, high annotation efforts and costs are commonly needed to acquire sufficient biomedical training data for DL models. To alleviate the burden of manual annotation, in this paper, we propose a new weakly supervised DL approach for biomedical image segmentation using boxes only annotation. First, we develop a method to combine graph search (GS) and DL to generate fine object masks from box annotation, in which DL uses box annotation to compute a rough segmentation for GS and then GS is applied to locate the optimal object boundaries. During the mask generation process, we carefully utilize information from box annotation to filter out potential errors, and then use the generated masks to train an accurate DL segmentation network. Extensive experiments on gland segmentation in histology images, lymph node segmentation in ultrasound images, and fungus segmentation in electron microscopy images show that our approach attains superior performance over the best known state-of-the-art weakly supervised DL method and is able to achieve (1) nearly the same accuracy compared to fully supervised DL methods with far less annotation effort, (2) significantly better results with similar annotation time, and (3) robust performance in various applications.

cs.CV↗

arXiv2018

Effect of Samarium doping on the nucleation of fcc-Aluminum in undercooled liquids

The effect of Sm doping on the fcc-Al nucleation was investigated in Al-Sm liquids with low Sm concentrations (xSm) with molecular dynamics simulations. The nucleation in the moderately undercooled liquid is achieved by the recently developed persistent-embryo method. Systematically computing the nucleation rate with different xSm (xSm=0%, 1%, 2%, 3%, 5%) at 700 K, we found Sm dopant reduces the nucleation rate by up to 25 orders of magnitudes with only 5% doping concentration. This effect is mostly associated with the increase in the free energy barrier with a minor contribution from suppression of the attachment to the nucleus caused by Sm doping.

cond-mat.mtrl-sci↗

arXiv2018

Ultra Power-Efficient CNN Domain Specific Accelerator with 9.3TOPS/Watt for Mobile and Embedded Applications

Computer vision performances have been significantly improved in recent years by Convolutional Neural Networks(CNN). Currently, applications using CNN algorithms are deployed mainly on general purpose hardwares, such as CPUs, GPUs or FPGAs. However, power consumption, speed, accuracy, memory footprint, and die size should all be taken into consideration for mobile and embedded applications. Domain Specific Architecture (DSA) for CNN is the efficient and practical solution for CNN deployment and implementation. We designed and produced a 28nm Two-Dimensional CNN-DSA accelerator with an ultra power-efficient performance of 9.3TOPS/Watt and with all processing done in the internal memory instead of outside DRAM. It classifies 224x224 RGB image inputs at more than 140fps with peak power consumption at less than 300mW and an accuracy comparable to the VGG benchmark. The CNN-DSA accelerator is reconfigurable to support CNN model coefficients of various layer sizes and layer types, including convolution, depth-wise convolution, short-cut connections, max pooling, and ReLU. Furthermore, in order to better support real-world deployment for various application scenarios, especially with low-end mobile and embedded platforms and MCUs (Microcontroller Units), we also designed algorithms to fully utilize the CNN-DSA accelerator efficiently by reducing the dependency on external accelerator computation resources, including implementation of Fully-Connected (FC) layers within the accelerator and compression of extracted features from the CNN-DSA accelerator. Live demos with our CNN-DSA accelerator on mobile and embedded systems show its capabilities to be widely and practically applied in the real world.

cs.CV↗

arXiv2018

Configurations and Diagnosis for Ultra-Dense Heterogeneous Networks: From Empirical Measurements to Technical Solutions

The intense demands for higher data rates and ubiquitous network coverage have raised the stakes on developing new network topology and architecture to meet these ever-increasing demands in a cost-effective manner. The telecommunication industry and international standardization bodies have placed considerable attention to the deployment of ultra-dense heterogeneous small-scale cells over existing cellular systems. Those small-scale cells, although provide higher data rates and better indoor coverage by reducing the distance between base stations (BSs) and end users, have raised severe configuration concerns. As the deployments are becoming irregular and flexible, inappropriate configurations occur frequently and undermine the network reliability and service quality. We envision that the fine-grained characterization of user traffic is a key pillar to diagnosing inappropriate configurations. In this article, we investigate the fine-grained traffic patterns of mobile users by analyzing the network data containing millions of subscribers and covering thousands of cells in a large metropolitan area. We characterize traffic patterns and mobility behaviors of users and geospatial properties of cells, and discuss how the heterogeneity of these characteristics affects network configurations and diagnosis in future ultra-dense small cells. Based on these observations from our measurements, we investigate possible models and corresponding challenges, and propose a heterogeneity-aware scheme that takes into account the disparity of user mobility behaviors and geospatial properties among small cells.

cs.NI↗