Evaluation of segmentation algorithms for extraction of RNFL in OCT images

The thickness of the retinal nerve fiber layer (RFNL) has become a diagnose measure for glaucoma assessment. To measure this thickness, accurate segmentation of the RFNL in optical coherence tomography (OCT) images is essential. Identification of a suitable segmentation algorithm will facilitate the enhancement of the RNFL thickness measurement accuracy. This paper investigates the performance of six algorithms in the segmentation of RNFL in OCT images. The algorithms are: normalised cuts, region growing, k-means clustering, active contour, level sets segmentation: Piecewise Gaussian Method (PGM) and Kernelized Method (KM). The performance of the six algorithms are determined through a set of experiments on OCT retinal images. An experimental procedure is used to measure the performance of the tested algorithms. The measured segmentation precision-recall results of the six algorithms are compared and discussed.

Scenarios involving future climate and water extraction: ecosystem states in the estuary of Australia's largest river

 

Extraction of latent patterns and contexts from social honest signals using hierarchical Dirichlet processes

A fundamental task in pervasive computing is reliable acquisition of contexts from sensor data. This is crucial to the operation of smart pervasive systems and services so that they might behave efficiently and appropriately upon a given context. Simple forms of context can often be extracted directly from raw data. Equally important, or more, is the hidden context and pattern buried inside the data, which is more challenging to discover. Most of existing approaches borrow methods and techniques from machine learning, dominantly employ parametric unsupervised learning and clustering techniques. Being parametric, a severe drawback of these methods is the requirement to specify the number of latent patterns in advance. In this paper, we explore the use of Bayesian nonparametric methods, a recent data modelling framework in machine learning, to infer latent patterns from sensor data acquired in a pervasive setting. Under this formalism, nonparametric prior distributions are used for data generative process, and thus, they allow the number of latent patterns to be learned automatically and grow with the data - as more data comes in, the model complexity can grow to explain new and unseen patterns. In particular, we make use of the hierarchical Dirichlet processes (HDP) to infer atomic activities and interaction patterns from honest signals collected from sociometric badges. We show how data from these sensors can be represented and learned with HDP. We illustrate insights into atomic patterns learned by the model and use them to achieve high-performance clustering. We also demonstrate the framework on the popular Reality Mining dataset, illustrating the ability of the model to automatically infer typical social groups in this dataset. Finally, our framework is generic and applicable to a much wider range of problems in pervasive computing where one needs to infer high-level, latent patterns and contexts from sensor data.

Analysis of residues of prometryne and acetochlor in soil-water system by solid-phase extraction and gas chromatography/mass spectrometry

A highly sensitive and simple analytical method was developed for analyzing the binary mixed pesticides of prometryne and acetochlor in soil–water system by gas chromatography/mass spectrometry (GC/MS). The sample solution was first purified by C18 solid-phase extraction column, which was leached by acetone. The leachate was enriched to 1.0 mL by pressure blowing concentrator and then analyzed by GC/MS. The linear calibration curves were showed in the range of 1–15 μg/mL with a correlation coefficient of 0.9991. The average recoveries (n = 5) were between 95.3 and 115.7%, with relative standard deviations ranged from 1.71 and 7.95%. The limits of detection of Prometryne/Acetochlor were up to 0.06 and 0.17 μg/mL, respectively. This method provides a reliable approach to examine and evaluate the residues of prometryne and acetochlor in the soil–water system.

Blind extraction using fractional lower-order statistics

In traditional method to blindly extract interesting source signals sequentially, the second-order or higher-order statistics of signals are often utilized. However, for impulsive sources, both of the second-order and higher-order statistics may degenerate. Therefore, it is necessary to exploit new method for the blind extraction of impulsive sources. Based on the best compression-reconstruction principle, a novel model is proposed in this work, together with the corresponding algorithm. The proposed method can be used for blind extraction of sources which are distributed from alpha stable process. Simulations are given to illustrate availability and robustness of our algorithm.

Integrated RNA extraction and RT-PCR for semi-quantitative gene expression studies on a microfluidic device

This paper describes the development of a microfluidic methodology, using RNA extraction and reverse transcription PCR, for investigating expression levels of cytochrome P450 genes. Cytochrome P450 enzymes are involved in the metabolism of xenobiotics, including many commonly prescribed drugs, therefore information on their expression is useful in both pharmaceutical and clinical settings. RNA extraction, from rat liver tissue or primary rat hepatocytes, was performed using a silica-based solid-phase extraction technique. Following elution of the purified RNA, amplification of target sequences for the housekeeping gene, glyceraldehyde-3-phosphate dehydrogenase (GAPDH) and the cytochrome P450 gene CYP1A2, was carried out using a one-step reverse transcription PCR. Once the microfluidic methodology had been optimized, analysis of control and 3-methylcholanthrene-induced primary rat hepatocytes were used to evaluate the system. As expected, GAPDH was consistently expressed, whereas CYP1A2 levels were found to be raised in the drug-treated samples. The proposed system offers an initial platform for development of both rapid throughput analyzers for pharmaceutical drug screening and point-of-care diagnostic tests to aid provision of drug regimens, which can be tailor-made to the individual patient.