Supervised Pattern Recognition Methods Research Articles

Nosologic imaging of the brain: segmentation and classification using MRI and MRSI

A new technique is presented to create nosologic images of the brain based on magnetic resonance imaging (MRI) and magnetic resonance spectroscopic imaging (MRSI). A nosologic image summarizes the presence of different tissues and lesions in a single image by color coding each voxel or pixel according to the histopathological class it is assigned to. The proposed technique applies advanced methods from image processing as well as pattern recognition to segment and classify brain tumors. First, a registered brain atlas and a subject-specific abnormal tissue prior, obtained from MRSI data, are used for the segmentation. Next, the detected abnormal tissue is classified based on supervised pattern recognition methods. Class probabilities are also calculated for the segmented abnormal region. Compared to previous approaches, the new framework is more flexible and able to better exploit spatial information leading to improved nosologic images. The combined scheme offers a new way to produce high-resolution nosologic images, representing tumor heterogeneity and class probabilities, which may help clinicians in decision making.

SUPERVISED PATTERN RECOGNITION TECHNIQUES FOR CLASSIFICATION OF EUCALYPTUS SPECIES FROM LEAVES NIR SPECTRA

Three supervised pattern recognition methods (SPRM) were evaluated to discriminate between Eucalyptus globulus and Eucalyptus nitens species applying near infrared (NIR) spectroscopy on leaves. The methods used were k-nearest neighbor (KNN), soft modeling class analogy (SIMCA) and discriminant partial least squares (PLS-DA). First and second derivatives were used as transform techniques and mean-center (MC) and autoscaling (AS) as preprocessing techniques. The training set was constitued by 288 samples and 20 samples were used as validation set. A significant difference between the assayed methods was not observed, however best results for separation of classes and prediction rate were obtained when first derivative and MC were used for all the recognition pattern methods. Use of leaves and NIR spectroscopy avoids the destructive usual wood analysis in forest industries and facilities the fast classification of these species for forest applications.

Simulated Radiance Profiles for Automating the Interpretation of Airborne Passive Multi-Spectral Infrared Images

Methodology is developed for simulating the radiance profiles acquired from airborne passive multispectral infrared imaging measurements of ground sources of volatile organic compounds (VOCs). The simulation model allows the superposition of pure-component laboratory spectra of VOCs onto spectral backgrounds that simulate those acquired during field measurements conducted with a downward-looking infrared line scanner mounted on an aircraft flying at an altitude of 2000-3000 ft (approximately 600-900 m). Wavelength selectivity in the line scanner is accomplished through the use of a multichannel Hg:Cd:Te detector with up to 16 integrated optical filters. These filters allow the detection of absorption and emission signatures of VOCs superimposed on the upwelling infrared background radiance within the instrumental field of view (FOV). By combining simulated radiance profiles containing analyte signatures with field-collected background signatures, supervised pattern recognition methods can be employed to train automated classifiers for use in detecting the signatures of VOCs during field measurements. The targeted application for this methodology is the use of the imaging system to detect releases of VOCs during emergency response scenarios. In the work described here, the simulation model is combined with piecewise linear discriminant analysis to build automated classifiers for detecting ethanol and methanol. Field data collected during controlled releases of ethanol, as well as during a methanol release from an industrial facility, are used to evaluate the methodology.

Fingerprinting of complex mixtures with the use of high performance liquid chromatography, inductively coupled plasma atomic emission spectroscopy and chemometrics

The molecular and metal profile fingerprints were obtained from a complex substance, Atractylis chinensis DC—a traditional Chinese medicine (TCM), with the use of the high performance liquid chromatography (HPLC) and inductively coupled plasma atomic emission spectroscopy (ICP-AES) techniques. This substance was used in this work as an example of a complex biological material, which has found application as a TCM. Such TCM samples are traditionally processed by the Bran, Cut, Fried and Swill methods, and were collected from five provinces in China. The data matrices obtained from the two types of analysis produced two principal component biplots, which showed that the HPLC fingerprint data were discriminated on the basis of the methods for processing the raw TCM, while the metal analysis grouped according to the geographical origin. When the two data matrices were combined into a one two-way matrix, the resulting biplot showed a clear separation on the basis of the HPLC fingerprints. Importantly, within each different grouping the objects separated according to their geographical origin, and they ranked approximately in the same order in each group. This result suggested that by using such an approach, it is possible to derive improved characterisation of the complex TCM materials on the basis of the two kinds of analytical data. In addition, two supervised pattern recognition methods, K-nearest neighbors (KNNs) method, and linear discriminant analysis (LDA), were successfully applied to the individual data matrices—thus, supporting the PCA approach.

Differentiation of ‘two Andalusian DO ‘fino’ wines according to their metal content from ICP-OES by using supervised pattern recognition methods

The metal content (Ca, Mg, Sr, Ba, K, Na, P, Fe, Al, Mn, Cu and Zn) of several ‘fino’ wines belonging to two Andalusian Denomination of Origin (DO) was determined by ICP-OES. Metal concentrations were selected as chemical descriptors for discrimination, because they play a primary role in the discrimination due to its correlation with soil nature, geographical origin and grape variety. The two studied Andalusian DO were the Jerez-Xérès-Sherry & Manzanilla-Sanlúcar de Barrameda (class D) and the Condado de Huelva (class C). Linear Discriminant Analysis (LDA) and procedures based on Artificial Neural Networks (ANN) leads to a perfect separation of classes, especially when applying Multi Layer Perceptrons ANN trained by back-propagation.

Structure modelling and discrimination of Catalan white wines

Cluster analysis has been applied to characterized the group structures of four sets of Catalan white wines (Conca de Barbera, Camp de Tarragona, Terra Alta and Ribera-Falset) on the basis of eleven classical oenological parameters and seven micro and trace metallic constitutents considered to be relatively insensitive to cultural practices. In spite of the vintage variation and the lack of a clear varietal differentiation among the wines, each region could be individually characterized. The application of supervised pattern recognition methods has allowed regional assignment of unknown samples with a prediction rate higher than 95%. Several metal ions (such as calcium, strontium, zinc and magnesium) and a few classical parameters (such as ethanol content and the sum of malic and lactic acid contents) have been found to be relevant for a correct classification. ALLOC and KNN classification methods combined with LDA have been proven useful with the present data set, although their performance was not superior to that of LDA and SIMCA.

Chemometric classification of Basque and French ciders based on their total polyphenol contents and CIELab parameters

Total polyphenol contents, estimated by Folin–Ciocalteu method, and CIELab chromatic parameters were determined in Basque and French ciders with the aim of developing a classification system to confirm the authenticity of ciders. A preliminary study of data structure was performed by a multivariate data analysis using chemometric techniques such as cluster analysis and principal component analysis. Supervised pattern recognition methods, such as linear discriminant analysis, K-nearest neighbours (KNN), soft independent modelling of class analogy and multilayer feed-forward artificial neural networks (MLF-ANN), provided classification rules for the two categories based on the experimental data. KNN results for Basque ciders afforded an excellent performance in terms of recognition and prediction abilities (99%), providing a useful tool to detect genuine Basque ciders. Despite KNN and MLF-ANN giving the best results for French ciders, with a success rate of prediction ability around 91%, this would not be acceptable for authentication purposes.

Comparison of supervised pattern recognition methods with McNemar’s statistical test: Application to qualitative analysis of sugar beet by near-infrared spectroscopy

The application of supervised pattern recognition methodology is becoming important within chemistry. The aim of the study is to compare classification method accuracies by the use of a McNemar’s statistical test. Three qualitative parameters of sugar beet are studied: disease resistance (DR), geographical origins and crop periods. Samples are analyzed by near-infrared spectroscopy (NIRS) and by wet chemical analysis (WCA). Firstly, the performances of eight well-known classification methods on NIRS data are compared: Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN) method, Soft Independent Modeling of Class Analogy (SIMCA), Discriminant Partial Least Squares (DPLS), Procrustes Discriminant Analysis (PDA), Classification And Regression Tree (CART), Probabilistic Neural Network (PNN) and Learning Vector Quantization (LVQ) neural network are computed. Among the three data sets, SIMCA, DPLS and PDA have the highest classification accuracies. LDA and KNN are not significantly different. The non-linear neural methods give the less accurate results. The three most accurate methods are linear, non-parametric and based on modeling methods. Secondly, we want to emphasize the power of near-infrared reflectance data for sample discrimination. McNemar’s tests compare classification developed with WCA or with NIRS data. For two of the three data sets, the classification results are significantly improved by the use of NIRS data.

Hirsutism: A multivariate approach of feature selection and classification

Abstract Armanino, C., Lanteri, S., Forina, M., Balsamo, A., Migliardi, M. and Cenderelli, G., 1989. Hirsutism: a multivariate approach of feature selection and classification. Chemometrics and Intelligent Laboratory Systems, 5: 335–341. Supervised pattern recognition methods were applied to the results of seven hormonal tests from a population of twenty-six healthy subjects and one hundred and seven women affected by hirsutism, in order to study the discriminant information from analytical data. Eigenvector projection and raw Varimax rotation, a stepwise multivariate method of feature selection based on quadratic discriminant analysis, the classification methods of k-nearest neighbours and quadratic discriminant analysis were applied. The prediction ability of the multivariate normal models, built by five selected variables (testosterone—estradiol binding globulin, dehydroepiandrosterone sulphate, estrone, salivary testosterone, 17β-estradiol) was 87.5%. Hierarchical clustering was carried out on the analytical data from the group of hirsute patients: two principal clusters and one singleton were identified.

Supervised Pattern Recognition Techniques in Quantitative Diagnostic Ultrasound

The methods of statistical pattern recognition are well suited to the problems of in vivo ultrasonic tissue characterization. This paper describes supervised pattern recognition methods for selecting features for tissue classification, calculating decision boundaries within the selected feature space, and evaluating the performance. We address the considerations of dimensionality and feature size which are important in classification problems where the underlying probability distributions are not completely known. Examples are given for the detection of diffuse liver disease in the clinical environment.

Pattern recognition study of biochemical assays for liver function

To extract discriminant information from analytical data, results from eight conventional biochemical tests of liver function and from determinations of two serum bile acids are studied by supervised pattern recognition methods. The population comprised healthy subjects and seven groups of people affected by different liver diseases. The principal components, linear discriminant, k nearest neighbours and Bayesian methods were applied. Because the prediction ability computed on the whole data set was poor, the problem was simplified by dividing the data set into three subsets, each comprising two liver diseases which were contiguous and overlapped in the hyperspace of variables. The prediction ability of the Bayesian method reached 96% at best, 75% at minimum, in the three subsets. Best performance was achieved in distinguishing between healthy subjects and those with mild liver diseases on the basis of four biochemical assays.