Pathological brain detection in MRI scanning via Hu moment invariants and machine learning

Abstract

Background: We proposed a new automatic and rapid computer-aided diagnosis system to detect pathological brain images obtained in the scans of magnetic resonance imaging (MRI). Methods: For simplification, we transformed the problem to a binary classification task (pathological or normal). It consisted of two steps: first, Hu moment invariants (HMI) were extracted from a specific MR brain image; then, seven HMI features were fed into two classifiers: twin support vector machine (TSVM) and generalised eigenvalue proximal SVM (GEPSVM). Results: Then, a 5 × 5-fold cross validation on a data set containing 90 MR brain images, demonstrated that the proposed methods “HMI + GEPSVM” and “HMI + TSVM” achieved classification accuracy of 98.89%, higher than eight state-of-the-art methods: “DWT + PCA + BP-NN”, “DWT + PCA + RBF-NN”, “DWT + PCA + PSO-KSVM”, “WE + BP-NN”, “WE + KSVM”, “DWT + PCA + GA-KSVM”, “WE + PSO-KSVM” and “WE + BBO-KSVM”. Conclusion: The proposed methods are superior to other methods on pathological brain detection (p < 0.05).     

The GenBank nucleic acid sequence database

The GenBank nucleic acid sequence database is a computer-based collection of all published DNA and RNA sequences; it contains over five million bases in close to six thousand sequence entries drawn from four thousand five hundred published articles. Each sequence is accompanied by relevant biological annotation. The database is available either on magnetic tape, on floppy diskettes, on-line or in hardcopy form. We discuss the structure of the database, the extent of the data and the implications of the database for research on nucleic acids.     

An integrated microfluidic system using mannose-binding lectin for bacteria isolation and biofilm-related gene detection

Molecular diagnosis of biofilm-related genes (BRGs) in common bacteria that cause periprosthetic joint infections may provide crucial information for clinicians. In this study, several BRGs, including ica, fnbA, and fnbB, were rapidly detected (within 1 h) with a new integrated microfluidic system. Mannose-binding lectin (MBL)-coated magnetic beads were used to isolate these bacteria, and on-chip nucleic acid amplification (polymerase chain reaction, PCR) was then performed to detect BRGs. Both eukaryotic and prokaryotic MBLs were able to isolate common bacterial strains, regardless of their antibiotic resistance, and limits of detection were as low as 3 and 9 CFU for methicillin-resistant Staphylococcus aureus and Escherichia coli, respectively, when using a universal 16S rRNA PCR assay for bacterial identification. It is worth noting that the entire process including bacteria isolation by using MBL-coated beads for sample pre-treatment, on-chip PCR, and fluorescent signal detection could be completed on an integrated microfluidic system within 1 h. This is the first time that an integrated microfluidic system capable of detecting BRGs by using MBL as a universal capturing probe was reported. This integrated microfluidic system might therefore prove useful for monitoring profiles of BRGs and give clinicians more clues for their clinical judgments in the near future.     

碳纳米管修饰电极的制备及其对NADH的电催化氧化

采用丝网印刷技术,制备出羧基化多壁碳纳米管修饰的丝网印刷碳电极,并采用循环伏安法研究了该电极对还原型烟酰胺腺嘌呤二核苷酸(NADH)的电催化氧化性能.结果表明,与未修饰丝网印刷碳电极相比,多壁碳纳米管修饰丝网印刷碳电极显著降低了NADH的氧化峰电位,消除了反应产物对电极的污染及其它电化学反应对测量的干扰.将修饰电极与流...     

A two-stage electrophoretic microfluidic device for nucleic acid collection and enrichment

Sample purification and enrichment is an important and usually time-consuming step for on-chip nucleic acid detection and analysis. This paper presents an electrophoretic DNA focusing method in microfluidic devices to enrich nucleic acid concentration by around 2700-fold. The electrical waveforms applied to five individual electrodes are such designed that DNAs move successively to the collection electrodes at high speed, while the interferences from bubbles due to electrohydrolysis are minimized. In a spiral channel with a total length of 48 cm, 1 ml DNA sample is purified and enriched by 57 times at a flow rate of 30 μl/min at first. The captured DNAs are then released and transported to the second microfluidic chamber where DNAs are collected and concentrated by 49 times. Thus, in about 40 min, the two-stage device can extract DNAs from 1 ml sample volume and enrich its concentration by 2790-fold. A trade-off exists between the process throughput and the DNA collection efficiency. A DNA capture efficiency of 99.7 % is reached when the flow rate is 1 μl/min, and the maximum DNA capture throughput is achieved at a flow rate of 30 μl/min. As a platform technology, the device can be integrated into bio-sensing and genetic analysis assays for DNA extraction and pre-concentration.     

Predictions of toughness and hardness by using chemical composition and tensile properties in microalloyed line pipe steels

Artificial neural networks with multilayer feed forward topology and back propagation algorithm containing two hidden layers are implemented to predict the effect of chemical composition and tensile properties on the both impact toughness and hardness of microalloyed API X70 line pipe steels. The chemical compositions in the forms of “carbon equivalent based on the International Institute of Welding equation (CE_IIW)”, “carbon equivalent based on the Ito-Bessyo equation (CE_Pcm)”, “the sum of niobium, vanadium and titanium concentrations (VTiNb)”, “the sum of niobium and vanadium concentrations (NbV)” and “the sum of chromium, molybdenum, nickel and copper concentrations (CrMoNiCu)”, as well as, tensile properties of “yield strength (YS)”, “ultimate tensile strength (UTS)” and “elongation (El)” are considered together as input parameters of networks while Vickers microhardness with 10 kgf applied load (HV10) and Charpy impact energy at ?10 °C (CVN ?10 °C) are assumed as the outputs of constructed models. For the purpose of constructing the models, 104 different measurements are performed and gathered data from examinations are randomly divided into training, testing and validating sets. Scatter plots and statistical criteria of “absolute fraction of variance (R²)”, and “mean relative error (MRE)” are used to evaluate the prediction performance and universality of the developed models. Based on analyses, the proposed models can be further used in practical applications and thermo-mechanical manufacturing processes of microalloyed steels.     

A pulsed plasma thruster fault detection and isolation strategy for formation flying of satellites

The main objective of this paper is to develop a dynamic neural network-based fault detection and isolation (FDI) scheme for pulsed plasma thrusters (PPTs) that are employed in the attitude control subsystem (ACS) of satellites tasked to perform formation flying (FF) missions. A hierarchical methodology is proposed that consists of three fault detection and isolation (FDI) approaches, namely (i) a “low-level” FDI scheme, (ii) a “high-level” FDI scheme, and (iii) an “integrated” FDI scheme. Based on the data from the electrical circuit of the PPTs, the proposed “low-level” FDI scheme can detect and isolate faults in the PPT actuators with a good level of accuracy, however the precision level is poor and below expectations with the misclassification rates as expressed by False Healthy and False Faulty parameters being too high. The proposed “high-level” FDI scheme utilizes data from the relative attitudes of the FF mission. This scheme has good detection capabilities, however its isolation capabilities are not adequate. Finally, the proposed “integrated” FDI scheme takes advantage of the strengths of each of the above two schemes while reducing their individual weaknesses. The results demonstrate a high level of accuracy (99.79%) and precision (99.94%) with a misclassification rates that are quite negligible (less than 1%). Furthermore, the proposed “integrated” FDI scheme provides additional and interesting information related to the effects of faults in the thrust production levels that would not have been available from simply using the low or the high level schemes alone.     

A novel method for alignment of two nucleic acid sequences using ant colony optimization and genetic algorithms

We describe a new method for pairwise nucleic acid sequence alignment that can also be used for pattern searching and tandem repeat searching within a nucleic acid sequence. The method is broadly a hybrid algorithm employing ant colony optimization (ACO) and the simple genetic algorithm. The method first employs ACO to obtain a set of alignments, which are then further processed by an elitist genetic algorithm, which employs primitive selection and a novel multipoint crossover-mutation operator to generate accurate alignments. The resulting alignments show a fair amount of accuracy for smaller and medium size sequences. Furthermore, this algorithm can be used rather quickly and efficiently for aligning shorter sequences and also for pattern searching in both nucleic acid and amino acid sequences. Furthermore, it can be used as an effective local alignment method or as a global alignment tool. On improvement of accuracy, this method can be extended for use towards multiple sequence alignment.     

Comparative performance evaluation of carbon dot-based paper immunoassay on Whatman filter paper and nitrocellulose paper in the detection of HIV infection

Carbon dots synthesized from citric acid and ethylene diamine by a one-step hydrothermal technique were used to develop a carbon dot-based paper immunoassay (CDPIA) for rapid detection of HIV-1 p24 antigen. In the present study, the 96-well template was hand patterned using a wax pencil, as a prototype method, on two types of paper, (1) Whatman filter paper and (2) nitrocellulose paper. The sandwich immunoassay was performed on both paper microplates for detection of HIV-1 p24 antigen which is an early marker of HIV infection. The detection range was from 10 μg/mL to 1 ng/mL for the Whatman filter paper while the nitrocellulose paper exhibited a higher range from 10 μg/mL to 250 pg/mL. CDPIA on the nitrocellulose paper (CDNIA) exhibited a fourfold increase in sensitivity and reduced the assay time by threefold compared with CDPIA on Whatman paper (CDWIA). HIV-negative and HIV-positive plasma samples were tested using CDNIA for the presence of HIV-1 p24 antigen. This immunoassay exhibited no false-positive and false-negative results with the clinical samples tested. This simple and sensitive paper-based HIV-1 p24 antigen assay may be useful in preventing HIV transmission by blood transfusion in resource-limited settings by reducing the antibody negative, infectious window period in blood donors and for early diagnosis of HIV infected individuals where nucleic acid-based testing is not practical or feasible.     

Development of carbon dot based microplate and microfluidic chip immunoassay for rapid and sensitive detection of HIV-1 p24 antigen

A highly sensitive, precisely specific, environmentally friendly, high-throughput, microwell-plate and microchip-based sandwich assay was developed to detect HIV-1 p24 antigen, a protein biomarker using fluorescent carbon dots. High quantum yield carbon dots were synthesized using citric acid and ethylenediamine as carbon and nitrogen sources by a single-step hydrothermal reaction. The desired amine groups confirmed by FTIR on the carbon dots were coupled to streptavidin by amine–amine coupling reaction using glutaraldehyde. The detection range of the carbon dot based immunoassay (CDIA) was found to be between 20 and 1000 pg/mL in a linear dose-dependent manner. CDIA tested for HIV negative plasma samples showed no false positive results in the detection of HIV-1 p24 antigen. The CDIA was extended to develop a microfluidic carbon dot immunoassay (μCDIA) which exhibited analytical sensitivity in the range of 30–1000 pg/mL. The CDIA and μCDIA can easily be adapted to a lab-on-a-chip platform for use in resource limited settings and can also be multiplexed for the detection of other pathogens like TB and Hepatitis.     

Exercise classification and event segmentation in Hammersmith Infant Neurological Examination videos

Image and video processing techniques are being frequently used in medical science applications. Computer vision-based systems have successfully replaced various manual medical processes such as analyzing physical and biomechanical parameters, physical examination of patients. These systems are gaining popularity because of their robustness and the objectivity they bring to various medical procedures. Hammersmith Infant Neurological Examinations (HINE) is a set of physical tests that are carried out on infants in the age group of 3–24 months with neurological disorders. However, these tests are graded through visual observations, which can be highly subjective. Therefore, computer vision-aided approach can be used to assist the experts in the grading process. In this paper, we present a method of automatic exercise classification through visual analysis of the HINE videos recorded at hospitals. We have used scale-invariant-feature-transform features to generate a bag-of-words from the image frames of the video sequences. Frequency of these visual words is then used to classify the video sequences using HMM. We also present a method of event segmentation in long videos containing more than two exercises. Event segmentation coupled with a classifier can help in automatic indexing of long and continuous video sequences of the HINE set. Our proposed framework is a step forward in the process of automation of HINE tests through computer vision-based methods. We conducted tests on a dataset comprising of 70 HINE video sequences. It has been found that the proposed method can successfully classify exercises with accuracy as high as 84%. The proposed work has direct applications in automatic or semiautomatic analysis of “vertical suspension” and “ventral suspension” tests of HINE. Though some of the critical tests such as “pulled-to-sit,” “lateral tilting,” or “adductor’s angle measurement” have already been addressed using image- and video-guided techniques, scopes are there for further improvement.     

Lower Bounds for Runtime Complexity of Term Rewriting

We present the first approach to deduce lower bounds for (worst-case) runtime complexity of term rewrite systems (TRSs) automatically. Inferring lower runtime bounds is useful to detect bugs and to complement existing methods that compute upper complexity bounds. Our approach is based on two techniques: the induction technique generates suitable families of rewrite sequences and uses induction proofs to find a relation between the length of a rewrite sequence and the size of the first term in the sequence. The loop detection technique searches for “decreasing loops”. Decreasing loops generalize the notion of loops for TRSs, and allow us to detect families of rewrite sequences with linear, exponential, or infinite length. We implemented our approach in the tool AProVE and evaluated it by extensive experiments.     

The implementation guidance for practicing network isolation by referring to ISO-17799 standard

In these years, the company budgets are raised dramatically for eliminating the security problems or mitigating the security risks in companies, but the numbers of incidents happening on computer systems in intranet or internet are still increasing. Many researchers proposed the way–to isolate the computers storing sensitive information for preventing information on these computers revealed or vulnerability on these computers exploited. However, there are few materials available for implementing network isolation. In this paper, we define ways of network isolation, “physical isolation” and “logical isolation”. In ISO-17799, there is no implementation guidance for practicing network logical isolation but auditing network physical isolation. This paper also provides the implementation guidance of network isolation in two aspects. One is for the technique viewpoints. The other aspect is for management viewpoints. These proposed implementation outlines and security measures will be considered in revising the security plan, “The Implementation Plan for Information Security Level in Government Departments” [“The implementation plan for information security level in government departments,” National Information and Communication Security Taskforce, Taiwan R.O.C., Programs, Jul. 20 2005].     

A disposable electrochemical immunofiltration test strip for rapid detection of α-fetoprotein

A disposable electrochemical immunofiltration test strip for the rapid detection of α-fetoprotein (AFP) was developed. The test strip was constructed by assembly of screen-printed carbon electrodes, absorption-water pad, nitrocellulose membrane modified by anti-AFP antibody and glass fiber membrane conjugated with ferrocene monocarboxylic acid (FC) labeling AFP. The analytical system utilizes flow-through immunofiltration and competitive immunoassay techniques in combination with an amperometric sensor. The parameters affecting the immunoassay such as selection of filter membrane, membrane pore-size, and antibody binding capacity were investigated and optimized. The immunofiltration system allows us to specifically and directly detect AFP in serum with a low detection limit of 6 ng/mL. The working range is from 6 to 500 ng/mL with an overall analysis time of 5 min for one sample. This electrochemical immunoassay system enabled us to construct a novel point-of-care testing device for the monitoring of biomarker including AFP.     

Meter-scale large-area capacitive pressure sensors with fabric with stripe electrodes of conductive polymer-coated fibers

We developed meter-scale large-area capacitive fabric pressure sensors for floor sensors to monitor human position. In the fabric pressure sensor, two fabrics with stripe electrodes of conductive polymer-coated fibers woven into them were stacked vertically, and the capacitance changes between the top and bottom stripe electrodes were measured when pressure was applied. By using the die-coating of a conductive polymer and weaving the resultant fibers with meter-scale automatic looming machines, the 1 m × 1 m area with stripe electrodes at a 20 cm pitch was constructed. The pressure sensitivity, which depends on the number of the sensor fibers forming the stripe electrodes, was characterized and optimized to increase output capacitance change. The stripe electrodes with five sensor fibers were found to exhibit a capacitance change of 1.37 pF when pushed with the average foot pressure (i.e., 2.6 N/cm²), which is large enough to detect with conventional capacitance measurement circuits. Finally, pressure sensing with our woven pressure sensor fabric is demonstrated. Our meter-scale pressure sensor fabric technology will be used for bed and floor sensors for monitoring old people in nursing homes and hospitals.     

Backwards Principal Component Analysis and Principal Nested Relations

In non-Euclidean data spaces represented by manifolds (or more generally stratified spaces), analogs of principal component analysis can be more easily developed using a backwards approach. There has been a gradual evolution in the application of this idea from using increasing geodesic subspaces of submanifolds in analogy with PCA to using a “backward sequence” of a decreasing family of subspaces. We provide a version of the backwards approach by using a “nested sequence of relations” which define the decreasing sequences of subspaces which need not be geodesic. Because these are naturally inductively added in a backward sequence, they are frequently more tractable and overcome difficulties with using geodesics.     

A set of Macintosh computer programs for the design and analysis of synthetic genes

Computer programs that can be used for the design of synthetic genes and that are run on an Apple Macintosh computer are described. These programs determine nucleic acid sequences encoding amino acid sequences. They select DNA sequences based on codon usage as specified by the user, and determine the placement of base changes that can be used to create restriction enzyme sites without altering the amino acid sequence. A new algorithm for finding restriction sites by translating the restriction endonuclease target sequence in all three reading frames and then searching the given peptide or protein amino acid sequence with these short restriction enzyme peptide sequences is described. Examples are given for the creation of synthetic DNA sequences for the bovine prethrombin-2 and ribonuclease A genes.     

DNA一级序列不同编码方法和相似度比较

为了DNA一级序列的相似度计算,本文比较了三种编码方案:单一碱基在DNA序列中的相对位置、二联码即相邻二碱基在序列中的相对位置、编序单一碱基在DNA序列中的相对位置和二联码在序列中的编序相对位置,在此基础上,运用分子连接性指数计算得到序列的不变量,进而,由塔尼莫特法计算得到物种间的相似度。由单一碱基在DNA序列中的相对位置法比较相似度,对于本研究中10个物种,得到了与生物进化树非常相一致的结果。     

Extreme learning machine assessment for estimating sediment transport in open channels

The minimum velocity required to prevent sediment deposition in open channels is examined in this study. The parameters affecting transport are first determined and then categorized into different dimensionless groups, including “movement,” “transport,” “sediment,” “transport mode,” and “flow resistance.” Six different models are presented to identify the effect of each of these parameters. The feed-forward neural network (FFNN) is used to predict the densimetric Froude number (Fr) and the extreme learning machine (ELM) algorithm is utilized to train it. The results of this algorithm are compared with back propagation (BP), genetic programming (GP) and existing sediment transport equations. The results indicate that FFNN-ELM produced better results than FNN-BP, GP and existing sediment transport methods in both training (RMSE = 0.26 and MARE = 0.052) and testing (RMSE = 0.121 and MARE = 0.023). Moreover, the performance of FFNN-ELM is examined for different pipe diameters.