Searcharxiv⌕ Search

arXiv subjects

Dongxiao Zhu

Publications and source records attributed to Dongxiao Zhu.

At least 55 records · Page 3Linked to original sources
arXiv2020

COVID-MobileXpert: On-Device COVID-19 Patient Triage and Follow-up using Chest X-rays

During the COVID-19 pandemic, there has been an emerging need for rapid, dedicated, and point-of-care COVID-19 patient disposition techniques to optimize resource utilization and clinical workflow. In view of this need, we present COVID-MobileXpert: a lightweight deep neural network (DNN) based mobile app that can use chest X-ray (CXR) for COVID-19 case screening and radiological trajectory prediction. We design and implement a novel three-player knowledge transfer and distillation (KTD) framework including a pre-trained attending physician (AP) network that extracts CXR imaging features from a large scale of lung disease CXR images, a fine-tuned resident fellow (RF) network that learns the essential CXR imaging features to discriminate COVID-19 from pneumonia and/or normal cases with a small amount of COVID-19 cases, and a trained lightweight medical student (MS) network to perform on-device COVID-19 patient triage and follow-up. To tackle the challenge of vastly similar and dominant fore- and background in medical images, we employ novel loss functions and training schemes for the MS network to learn the robust features. We demonstrate the significant potential of COVID-MobileXpert for rapid deployment via extensive experiments with diverse MS architecture and tuning parameter settings. The source codes for cloud and mobile based models are available from the following url: https://github.com/xinli0928/COVID-Xray.

eess.IV↗
arXiv2020

Explainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability

Latent factor collaborative filtering (CF) has been a widely used technique for recommender system by learning the semantic representations of users and items. Recently, explainable recommendation has attracted much attention from research community. However, trade-off exists between explainability and performance of the recommendation where metadata is often needed to alleviate the dilemma. We present a novel feature mapping approach that maps the uninterpretable general features onto the interpretable aspect features, achieving both satisfactory accuracy and explainability in the recommendations by simultaneous minimization of rating prediction loss and interpretation loss. To evaluate the explainability, we propose two new evaluation metrics specifically designed for aspect-level explanation using surrogate ground truth. Experimental results demonstrate a strong performance in both recommendation and explaining explanation, eliminating the need for metadata. Code is available from https://github.com/pd90506/AMCF.

cs.LG↗
arXiv2020

Defending against adversarial attacks on medical imaging AI system, classification or detection?

Medical imaging AI systems such as disease classification and segmentation are increasingly inspired and transformed from computer vision based AI systems. Although an array of adversarial training and/or loss function based defense techniques have been developed and proved to be effective in computer vision, defending against adversarial attacks on medical images remains largely an uncharted territory due to the following unique challenges: 1) label scarcity in medical images significantly limits adversarial generalizability of the AI system; 2) vastly similar and dominant fore- and background in medical images make it hard samples for learning the discriminating features between different disease classes; and 3) crafted adversarial noises added to the entire medical image as opposed to the focused organ target can make clean and adversarial examples more discriminate than that between different disease classes. In this paper, we propose a novel robust medical imaging AI framework based on Semi-Supervised Adversarial Training (SSAT) and Unsupervised Adversarial Detection (UAD), followed by designing a new measure for assessing systems adversarial risk. We systematically demonstrate the advantages of our robust medical imaging AI system over the existing adversarial defense techniques under diverse real-world settings of adversarial attacks using a benchmark OCT imaging data set.

cs.LG↗
arXiv2020

Vispi: Automatic Visual Perception and Interpretation of Chest X-rays

Medical imaging contains the essential information for rendering diagnostic and treatment decisions. Inspecting (visual perception) and interpreting image to generate a report are tedious clinical routines for a radiologist where automation is expected to greatly reduce the workload. Despite rapid development of natural image captioning, computer-aided medical image visual perception and interpretation remain a challenging task, largely due to the lack of high-quality annotated image-report pairs and tailor-made generative models for sufficient extraction and exploitation of localized semantic features, particularly those associated with abnormalities. To tackle these challenges, we present Vispi, an automatic medical image interpretation system, which first annotates an image via classifying and localizing common thoracic diseases with visual support and then followed by report generation from an attentive LSTM model. Analyzing an open IU X-ray dataset, we demonstrate a superior performance of Vispi in disease classification, localization and report generation using automatic performance evaluation metrics ROUGE and CIDEr.

cs.CV↗
arXiv2020

Tackling Ordinal Regression Problem for Heterogeneous Data: Sparse and Deep Multi-Task Learning Approaches

Many real-world datasets are labeled with natural orders, i.e., ordinal labels. Ordinal regression is a method to predict ordinal labels that finds a wide range of applications in data-rich domains, such as natural, health and social sciences. Most existing ordinal regression approaches work well for independent and identically distributed (IID) instances via formulating a single ordinal regression task. However, for heterogeneous non-IID instances with well-defined local geometric structures, e.g., subpopulation groups, multi-task learning (MTL) provides a promising framework to encode task (subgroup) relatedness, bridge data from all tasks, and simultaneously learn multiple related tasks in efforts to improve generalization performance. Even though MTL methods have been extensively studied, there is barely existing work investigating MTL for heterogeneous data with ordinal labels. We tackle this important problem via sparse and deep multi-task approaches. Specifically, we develop a regularized multi-task ordinal regression (MTOR) model for smaller datasets and a deep neural networks based MTOR model for large-scale datasets. We evaluate the performance using three real-world healthcare datasets with applications to multi-stage disease progression diagnosis. Our experiments indicate that the proposed MTOR models markedly improve the prediction performance comparing with single-task ordinal regression models.

cs.LG↗
arXiv2020

Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach

Existing aspect based sentiment analysis (ABSA) approaches leverage various neural network models to extract the aspect sentiments via learning aspect-specific feature representations. However, these approaches heavily rely on manual tagging of user reviews according to the predefined aspects as the input, a laborious and time-consuming process. Moreover, the underlying methods do not explain how and why the opposing aspect level polarities in a user review lead to the overall polarity. In this paper, we tackle these two problems by designing and implementing a new Multiple-Attention Network (MAN) approach for more powerful ABSA without the need for aspect tags using two new tag-free data sets crawled directly from TripAdvisor ({https://www.tripadvisor.com}). With the Self- and Position-Aware attention mechanism, MAN is capable of extracting both aspect level and overall sentiments from the text reviews using the aspect level and overall customer ratings, and it can also detect the vital aspect(s) leading to the overall sentiment polarity among different aspects via a new aspect ranking scheme. We carry out extensive experiments to demonstrate the strong performance of MAN compared to other state-of-the-art ABSA approaches and the explainability of our approach by visualizing and interpreting attention weights in case studies.

cs.CL↗
arXiv2020

On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks

Deep convolutional neural networks (CNNs) trained with logistic and softmax losses have made significant advancement in visual recognition tasks in computer vision. When training data exhibit class imbalances, the class-wise reweighted version of logistic and softmax losses are often used to boost performance of the unweighted version. In this paper, motivated to explain the reweighting mechanism, we explicate the learning property of those two loss functions by analyzing the necessary condition (e.g., gradient equals to zero) after training CNNs to converge to a local minimum. The analysis immediately provides us explanations for understanding (1) quantitative effects of the class-wise reweighting mechanism: deterministic effectiveness for binary classification using logistic loss yet indeterministic for multi-class classification using softmax loss; (2) disadvantage of logistic loss for single-label multi-class classification via one-vs.-all approach, which is due to the averaging effect on predicted probabilities for the negative class (e.g., non-target classes) in the learning process. With the disadvantage and advantage of logistic loss disentangled, we thereafter propose a novel reweighted logistic loss for multi-class classification. Our simple yet effective formulation improves ordinary logistic loss by focusing on learning hard non-target classes (target vs. non-target class in one-vs.-all) and turned out to be competitive with softmax loss. We evaluate our method on several benchmark datasets to demonstrate its effectiveness.

cs.LG↗
arXiv2020

CRCEN: A Generalized Cost-sensitive Neural Network Approach for Imbalanced Classification

Classification on imbalanced datasets is a challenging task in real-world applications. Training conventional classification algorithms directly by minimizing classification error in this scenario can compromise model performance for minority class while optimizing performance for majority class. Traditional approaches to the imbalance problem include re-sampling and cost-sensitive methods. In this paper, we propose a neural network model with novel loss function, CRCEN, for imbalanced classification. Based on the weighted version of cross entropy loss, we provide a theoretical relation for model predicted probability, imbalance ratio and the weighting mechanism. To demonstrate the effectiveness of our proposed model, CRCEN is tested on several benchmark datasets and compared with baseline models.

cs.LG↗
arXiv2020

Improve SGD Training via Aligning Mini-batches

Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of a feature extractor (i.e. last hidden layer) and a linear classifier (i.e. output layer) that is trained jointly with stochastic gradient descent (SGD). In each iteration of SGD, a mini-batch from the training data is sampled and the true gradient of the loss function is estimated as the noisy gradient calculated on this mini-batch. From the feature learning perspective, the feature extractor should be updated to learn meaningful features with respect to the entire data, and reduce the accommodation to noise in the mini-batch. With this motivation, we propose In-Training Distribution Matching (ITDM) to improve DNN training and reduce overfitting. Specifically, along with the loss function, ITDM regularizes the feature extractor by matching the moments of distributions of different mini-batches in each iteration of SGD, which is fulfilled by minimizing the maximum mean discrepancy. As such, ITDM does not assume any explicit parametric form of data distribution in the latent feature space. Extensive experiments are conducted to demonstrate the effectiveness of our proposed strategy.

cs.LG↗
arXiv2019

Representation Learning with Autoencoders for Electronic Health Records: A Comparative Study

Increasing volume of Electronic Health Records (EHR) in recent years provides great opportunities for data scientists to collaborate on different aspects of healthcare research by applying advanced analytics to these EHR clinical data. A key requirement however is obtaining meaningful insights from high dimensional, sparse and complex clinical data. Data science approaches typically address this challenge by performing feature learning in order to build more reliable and informative feature representations from clinical data followed by supervised learning. In this paper, we propose a predictive modeling approach based on deep learning based feature representations and word embedding techniques. Our method uses different deep architectures (stacked sparse autoencoders, deep belief network, adversarial autoencoders and variational autoencoders) for feature representation in higher-level abstraction to obtain effective and robust features from EHRs, and then build prediction models on top of them. Our approach is particularly useful when the unlabeled data is abundant whereas labeled data is scarce. We investigate the performance of representation learning through a supervised learning approach. Our focus is to present a comparative study to evaluate the performance of different deep architectures through supervised learning and provide insights in the choice of deep feature representation techniques. Our experiments demonstrate that for small data sets, stacked sparse autoencoder demonstrates a superior generality performance in prediction due to sparsity regularization whereas variational autoencoders outperform the competing approaches for large data sets due to its capability of learning the representation distribution.

cs.LG↗
arXiv2019

Representation Learning with Autoencoders for Electronic Health Records: A Comparative Study

Increasing volume of Electronic Health Records (EHR) in recent years provides great opportunities for data scientists to collaborate on different aspects of healthcare research by applying advanced analytics to these EHR clinical data. A key requirement however is obtaining meaningful insights from high dimensional, sparse and complex clinical data. Data science approaches typically address this challenge by performing feature learning in order to build more reliable and informative feature representations from clinical data followed by supervised learning. In this paper, we propose a predictive modeling approach based on deep learning based feature representations and word embedding techniques. Our method uses different deep architectures (stacked sparse autoencoders, deep belief network, adversarial autoencoders and variational autoencoders) for feature representation in higher-level abstraction to obtain effective and robust features from EHRs, and then build prediction models on top of them. Our approach is particularly useful when the unlabeled data is abundant whereas labeled data is scarce. We investigate the performance of representation learning through a supervised learning approach. Our focus is to present a comparative study to evaluate the performance of different deep architectures through supervised learning and provide insights in the choice of deep feature representation techniques. Our experiments demonstrate that for small data sets, stacked sparse autoencoder demonstrates a superior generality performance in prediction due to sparsity regularization whereas variational autoencoders outperform the competing approaches for large data sets due to its capability of learning the representation distribution

cs.LG↗
arXiv2019

Interpreting Age Effects of Human Fetal Brain from Spontaneous fMRI using Deep 3D Convolutional Neural Networks

Understanding human fetal neurodevelopment is of great clinical importance as abnormal development is linked to adverse neuropsychiatric outcomes after birth. Recent advances in functional Magnetic Resonance Imaging (fMRI) have provided new insight into development of the human brain before birth, but these studies have predominately focused on brain functional connectivity (i.e. Fisher z-score), which requires manual processing steps for feature extraction from fMRI images. Deep learning approaches (i.e., Convolutional Neural Networks) have achieved remarkable success on learning directly from image data, yet have not been applied on fetal fMRI for understanding fetal neurodevelopment. Here, we bridge this gap by applying a novel application of deep 3D CNN to fetal blood oxygen-level dependence (BOLD) resting-state fMRI data. Specifically, we test a supervised CNN framework as a data-driven approach to isolate variation in fMRI signals that relate to younger v.s. older fetal age groups. Based on the learned CNN, we further perform sensitivity analysis to identify brain regions in which changes in BOLD signal are strongly associated with fetal brain age. The findings demonstrate that deep CNNs are a promising approach for identifying spontaneous functional patterns in fetal brain activity that discriminate age groups. Further, we discovered that regions that most strongly differentiate groups are largely bilateral, share similar distribution in older and younger age groups, and are areas of heightened metabolic activity in early human development.

eess.IV↗
arXiv2018

Multi-task Prediction of Patient Workload

Developing reliable workload predictive models can affect many aspects of clinical decision making procedure. The primary challenge in healthcare systems is handling the demand uncertainty over the time. This issue becomes more critical for the healthcare facilities that provide service for chronic disease treatment because of the need for continuous treatments over the time. Although some researchers focused on exploring the methods for workload prediction recently, few types of research mainly focused on forecasting a quantitative measure for the workload of healthcare providers. Also, among the mentioned studies most of them just focused on workload prediction within one facility. The drawback of the previous studies is the problem is not investigated for multiple facilities where the quality of provided service, the equipment, and resources used for provided service as well as the diagnosis and treatment procedures may differ even for patients with similar conditions. To tackle the mentioned issue, this paper suggests a framework for patient workload prediction by using patients data from VA facilities across the US. To capture the information of patients with similar attributes and make the prediction more accurate, a heuristic cluster based algorithm for single task learning as well as a multi task learning approach are developed in this research.

cs.CY↗
arXiv2018

A Deep Active Survival Analysis Approach for Precision Treatment Recommendations: Application of Prostate Cancer

Survival analysis has been developed and applied in the number of areas including manufacturing, finance, economics and healthcare. In healthcare domain, usually clinical data are high-dimensional, sparse and complex and sometimes there exists few amount of time-to-event (labeled) instances. Therefore building an accurate survival model from electronic health records is challenging. With this motivation, we address this issue and provide a new survival analysis framework using deep learning and active learning with a novel sampling strategy. First, our approach provides better representation with lower dimensions from clinical features using labeled (time-to-event) and unlabeled (censored) instances and then actively trains the survival model by labeling the censored data using an oracle. As a clinical assistive tool, we introduce a simple effective treatment recommendation approach based on our survival model. In the experimental study, we apply our approach on SEER-Medicare data related to prostate cancer among African-Americans and white patients. The results indicate that our approach outperforms significantly than baseline models.

cs.LG↗
arXiv2017

SUBIC: A Supervised Bi-Clustering Approach for Precision Medicine

Traditional medicine typically applies one-size-fits-all treatment for the entire patient population whereas precision medicine develops tailored treatment schemes for different patient subgroups. The fact that some factors may be more significant for a specific patient subgroup motivates clinicians and medical researchers to develop new approaches to subgroup detection and analysis, which is an effective strategy to personalize treatment. In this study, we propose a novel patient subgroup detection method, called Supervised Biclustring (SUBIC) using convex optimization and apply our approach to detect patient subgroups and prioritize risk factors for hypertension (HTN) in a vulnerable demographic subgroup (African-American). Our approach not only finds patient subgroups with guidance of a clinically relevant target variable but also identifies and prioritizes risk factors by pursuing sparsity of the input variables and encouraging similarity among the input variables and between the input and target variables

cs.LG↗
arXiv2017

SAFS: A Deep Feature Selection Approach for Precision Medicine

In this paper, we propose a new deep feature selection method based on deep architecture. Our method uses stacked auto-encoders for feature representation in higher-level abstraction. We developed and applied a novel feature learning approach to a specific precision medicine problem, which focuses on assessing and prioritizing risk factors for hypertension (HTN) in a vulnerable demographic subgroup (African-American). Our approach is to use deep learning to identify significant risk factors affecting left ventricular mass indexed to body surface area (LVMI) as an indicator of heart damage risk. The results show that our feature learning and representation approach leads to better results in comparison with others.

cs.LG↗
arXiv2013

SPATA: A Seeding and Patching Algorithm for Hybrid Transcriptome Assembly

Transcriptome assembly from RNA-Seq reads is an active area of bioinformatics research. The ever-declining cost and the increasing depth of RNA-Seq have provided unprecedented opportunities to better identify expressed transcripts. However, the nonlinear transcript structures and the ultra-high throughput of RNA-Seq reads pose significant algorithmic and computational challenges to the existing transcriptome assembly approaches, either reference-guided or de novo. While reference-guided approaches offer good sensitivity, they rely on alignment results of the splice-aware aligners and are thus unsuitable for species with incomplete reference genomes. In contrast, de novo approaches do not depend on the reference genome but face a computational daunting task derived from the complexity of the graph built for the whole transcriptome. In response to these challenges, we present a hybrid approach to exploit an incomplete reference genome without relying on splice-aware aligners. We have designed a split-and-align procedure to efficiently localize the reads to individual genomic loci, which is followed by an accurate de novo assembly to assemble reads falling into each locus. Using extensive simulation data, we demonstrate a high accuracy and precision in transcriptome reconstruction by comparing to selected transcriptome assembly tools. Our method is implemented in assemblySAM, a GUI software freely available at http://sammate.sourceforge.net.

cs.CE↗
arXiv2013

SASeq: A Selective and Adaptive Shrinkage Approach to Detect and Quantify Active Transcripts using RNA-Seq

Identification and quantification of condition-specific transcripts using RNA-Seq is vital in transcriptomics research. While initial efforts using mathematical or statistical modeling of read counts or per-base exonic signal have been successful, they may suffer from model overfitting since not all the reference transcripts in a database are expressed under a specific biological condition. Standard shrinkage approaches, such as Lasso, shrink all the transcript abundances to zero in a non-discriminative manner. Thus it does not necessarily yield the set of condition-specific transcripts. Informed shrinkage approaches, using the observed exonic coverage signal, are thus desirable. Motivated by ubiquitous uncovered exonic regions in RNA-Seq data, termed as "naked exons", we propose a new computational approach that first filters out the reference transcripts not supported by splicing and paired-end reads, then followed by fitting a new mathematical model of per-base exonic coverage signal and the underlying transcripts structure. We introduce a tuning parameter to penalize the specific regions of the selected transcripts that were not supported by the naked exons. Our approach compares favorably with the selected competing methods in terms of both time complexity and accuracy using simulated and real-world data. Our method is implemented in SAMMate, a GUI software suite freely available from http://sammate.sourceforge.net

q-bio.QM↗