Weichuan Yu

Moving Object Detection by Detecting Contiguous Outliers in the Low-Rank Representation

Object detection is a fundamental step for automated video analysis in many vision applications. Object detection in a video is usually performed by object detectors or background subtraction techniques. Often, an object detector requires manually labeled examples to train a binary classifier, while background subtraction needs a training sequence that contains no objects to build a background model. To automate the analysis, object detection without a separate training phase becomes a critical task. People have tried to tackle this task by using motion information. But existing motion-based methods are usually limited when coping with complex scenarios such as nonrigid motion and dynamic background. In this paper, we show that the above challenges can be addressed in a unified framework named DEtecting Contiguous Outliers in the LOw-rank Representation (DECOLOR). This formulation integrates object detection and background learning into a single process of optimization, which can be solved by an alternating algorithm efficiently. We explain the relations between DECOLOR and other sparsity-based methods. Experiments on both simulated data and real sequences demonstrate that DECOLOR outperforms the state-of-the-art approaches and it can work effectively on a wide range of complex scenarios.

Comparison of public peak detection algorithms for MALDI mass spectrometry data analysis

BackgroundIn mass spectrometry (MS) based proteomic data analysis, peak detection is an essential step for subsequent analysis. Recently, there has been significant progress in the development of various peak detection algorithms. However, neither a comprehensive survey nor an experimental comparison of these algorithms is yet available. The main objective of this paper is to provide such a survey and to compare the performance of single spectrum based peak detection methods.ResultsIn general, we can decompose a peak detection procedure into three consequent parts: smoothing, baseline correction and peak finding. We first categorize existing peak detection algorithms according to the techniques used in different phases. Such a categorization reveals the differences and similarities among existing peak detection algorithms. Then, we choose five typical peak detection algorithms to conduct a comprehensive experimental study using both simulation data and real MALDI MS data.ConclusionThe results of comparison show that the continuous wavelet-based algorithm provides the best average performance.

Review Article: Stable feature selection for biomarker discovery

Feature selection techniques have been used as the workhorse in biomarker discovery applications for a long time. Surprisingly, the stability of feature selection with respect to sampling variations has long been under-considered. It is only until recently that this issue has received more and more attention. In this article, we review existing stable feature selection methods for biomarker discovery using a generic hierarchical framework. We have two objectives: (1) providing an overview on this new yet fast growing topic for a convenient reference; (2) categorizing existing methods under an expandable framework for future research and development.

SNPHarvester: a filtering-based approach for detecting epistatic interactions in genome-wide association studies

MOTIVATION Hundreds of thousands of single nucleotide polymorphisms (SNPs) are available for genome-wide association (GWA) studies nowadays. The epistatic interactions of SNPs are believed to be very important in determining individual susceptibility to complex diseases. However, existing methods for SNP interaction discovery either suffer from high computation complexity or perform poorly when marginal effects of disease loci are weak or absent. Hence, it is desirable to develop an effective method to search epistatic interactions in genome-wide scale. RESULTS We propose a new method SNPHarvester to detect SNP-SNP interactions in GWA studies. SNPHarvester creates multiple paths in which the visited SNP groups tend to be statistically associated with diseases, and then harvests those significant SNP groups which pass the statistical tests. It greatly reduces the number of SNPs. Consequently, existing tools can be directly used to detect epistatic interactions. By using a wide range of simulated data and a real genome-wide data, we demonstrate that SNPHarvester outperforms its recent competitor significantly and is promising for practical disease prognosis. AVAILABILITY http://bioinformatics.ust.hk/SNPHarvester.html.

Combinative multi-scale level set framework for echocardiographic image segmentation.

In the automatic segmentation of echocardiographic images, a priori shape knowledge has been used to compensate for poor features in ultrasound images. This shape knowledge is often learned via an off-line training process, which requires tedious human effort and is highly expertise-dependent. More importantly, a learned shape template can only be used to segment a specific class of images with similar boundary shape. In this paper, we present a multi-scale level set framework for segmentation of endocardial boundaries at each frame in a multiframe echocardiographic image sequence. We point out that the intensity distribution of an ultrasound image at a very coarse scale can be approximately modeled by Gaussian. Then we combine region homogeneity and edge features in a level set approach to extract boundaries automatically at this coarse scale. At finer scale levels, these coarse boundaries are used to both initialize boundary detection and serve as an external constraint to guide contour evolution. This constraint functions similar to a traditional shape prior. Experimental results validate this combinative framework.

GBOOST: a GPU-based tool for detecting gene–gene interactions in genome–wide case control studies

MOTIVATION Collecting millions of genetic variations is feasible with the advanced genotyping technology. With a huge amount of genetic variations data in hand, developing efficient algorithms to carry out the gene-gene interaction analysis in a timely manner has become one of the key problems in genome-wide association studies (GWAS). Boolean operation-based screening and testing (BOOST), a recent work in GWAS, completes gene-gene interaction analysis in 2.5 days on a desktop computer. Compared with central processing units (CPUs), graphic processing units (GPUs) are highly parallel hardware and provide massive computing resources. We are, therefore, motivated to use GPUs to further speed up the analysis of gene-gene interactions. RESULTS We implement the BOOST method based on a GPU framework and name it GBOOST. GBOOST achieves a 40-fold speedup compared with BOOST. It completes the analysis of Wellcome Trust Case Control Consortium Type 2 Diabetes (WTCCC T2D) genome data within 1.34 h on a desktop computer equipped with Nvidia GeForce GTX 285 display card. AVAILABILITY GBOOST code is available at http://bioinformatics.ust.hk/BOOST.html#GBOOST.

Predictive rule inference for epistatic interaction detection in genome-wide association studies

MOTIVATION Under the current era of genome-wide association study (GWAS), finding epistatic interactions in the large volume of SNP data is a challenging and unsolved issue. Few of previous studies could handle genome-wide data due to the difficulties in searching the combinatorially explosive search space and statistically evaluating high-order epistatic interactions given the limited number of samples. In this work, we propose a novel learning approach (SNPRuler) based on the predictive rule inference to find disease-associated epistatic interactions. RESULTS Our extensive experiments on both simulated data and real genome-wide data from Wellcome Trust Case Control Consortium (WTCCC) show that SNPRuler significantly outperforms its recent competitor. To our knowledge, SNPRuler is the first method that guarantees to find the epistatic interactions without exhaustive search. Our results indicate that finding epistatic interactions in GWAS is computationally attainable in practice. AVAILABILITY http://bioinformatics.ust.hk/SNPRuler.zip

Technical, bioinformatical and statistical aspects of liquid chromatography-mass spectrometry (LC-MS) and capillary electrophoresis-mass spectrometry (CE-MS) based clinical proteomics: A critical assessment

The search for biomarkers in biological fluids that can be used for disease diagnosis and prognosis using mass spectrometry has emerged to become a state-of-the-art methodology for clinical proteomics. Poor cross platform comparison of the findings, however, makes the need for comparison studies probably as urgent as the need for new ones. It is now increasingly recognized that standardized statistical and bioinformatics approaches during data processing are of utmost importance for such comparisons. This paper reviews two of the currently most promising methods, namely LC-MS and CE-MS techniques, and software tools used to analyze the huge amount of data they generate. We further review the statistical issues of feature selection and sample classification.

MegaSNPHunter: a learning approach to detect disease predisposition SNPs and high level interactions in genome wide association study

BackgroundThe interactions of multiple single nucleotide polymorphisms (SNPs) are highly hypothesized to affect an individuals susceptibility to complex diseases. Although many works have been done to identify and quantify the importance of multi-SNP interactions, few of them could handle the genome wide data due to the combinatorial explosive search space and the difficulty to statistically evaluate the high-order interactions given limited samples.ResultsThree comparative experiments are designed to evaluate the performance of MegaSNPHunter. The first experiment uses synthetic data generated on the basis of epistasis models. The second one uses a genome wide study on Parkinson disease (data acquired by using Illumina HumanHap300 SNP chips). The third one chooses the rheumatoid arthritis study from Wellcome Trust Case Control Consortium (WTCCC) using Affymetrix GeneChip 500K Mapping Array Set. MegaSNPHunter outperforms the best solution in this area and reports many potential interactions for the two real studies.ConclusionThe experimental results on both synthetic data and two real data sets demonstrate that our proposed approach outperforms the best solution that is currently available in handling large-scale SNP data both in terms of speed and in terms of detection of potential interactions that were not identified before. To our knowledge, MegaSNPHunter is the first approach that is capable of identifying the disease-associated SNP interactions from WTCCC studies and is promising for practical disease prognosis.

Towards pointwise motion tracking in echocardiographic image sequences--comparing the reliability of different features for speckle tracking.

In this paper, we studied the problem of feature-based motion tracking in echocardiographic image sequences. We described the relation between possible feature variations and different kinds of tissue motion using a linear convolution model. We also showed that motion-feature decorrelation (which means that the motion parameters estimated using feature tracking fail to represent the underlying tissue motion) compensation is an ill-posed inverse problem. Instead of finding a method that may provide better compensation results than previous approaches, we used an quantitative measure to compare the reliability of tracking features. Experiment results showed that the use of the reliability measure improved the robustness of displacement estimation. With the help of the reliability measure, we compared the performance of different features using simulations and phantom examples. While we noticed that the radio frequency (RF) signal outperforms the B-mode (BM) signal in the analysis of small deformation (e.g., less than 0.1% compression), we also found out that the BM signal works better than the RF signal in the analysis of large deformation (e.g., larger than 2% compression). The use of a band-passed filtered feature does not result in significant improvement in tracking.