Multi-category classification using an Extreme Learning Machine for microarray gene expression cancer diagnosis

In this paper, the recently developed Extreme Learning Machine (ELM) is used for direct multicategory classification problems in the cancer diagnosis area. ELM avoids problems like local minima, improper learning rate and overfitting commonly faced by iterative learning methods and completes the training very fast. We have evaluated the multi-category classification performance of ELM on three benchmark microarray datasets for cancer diagnosis, namely, the GCM dataset, the Lung dataset and the Lymphoma dataset. The results indicate that ELM produces comparable or better classification accuracies with reduced training time and implementation complexity compared to artificial neural networks methods like conventional back-propagation ANN, Linder's SANN, and Support Vector Machine methods like SVM-OVO and Ramaswamy's SVM-OVA. ELM also achieves better accuracies for classification of individual categories.     

Application of artificial neural network for classification of thyroid follicular tumors

OBJECTIVE: To analyze smears of 197 thyroid follicular tumors (adenoma and carcinoma). STUDY DESIGN: Several types of artificial neural networks (ANN) of various designs were used for diagnosis of thyroid follicular tumors. The typical complex of cytologic features, some nuclear morphometric parameters (area, perimeter, shape factor) and density features of chromatin texture (mean value and SD of gray levels) were defined for each tumor. RESULTS: The ANN was trained by means of cytologic features characteristic for a thyroid follicular adenoma and a follicular carcinoma. At subsequent testing, the correct cytologic diagnosis was established in 93% (25 of 27) of cases. The morphometry increased the accuracy of diagnosis for follicular tumors in up to 97% (75 of 78) of cases. ANN correctly distinguished an adenoma or a carcinoma in 87% (73 of 84) of cases when using color microscopic images of tumors. CONCLUSION: The usage of ANN has raised sensitivity of cytologic diagnosis of follicular tumors to 90%, compared with a usual cytologic method (sensitivity of 56%). The automatic classification of thyroid follicular tumors by means of ANN is prospective.     

Using an artificial neural network to characterize the relative suitability of environments for forest types in a complex tropical vegetation mosaic

A predictive understanding of the environmental controls on forest distributions is essential for the conservation of biodiversity and management of landscapes in the tropics. This is particularly true now because of potentially rapid climate change. The floristic complexity of tropical forests and the lack or absence of data severely limits the applicability of modelling methods based on the ecology or distribution of individual species. Here we present an artificial neural network (ANN) model using the information available in the humid tropics of North Queensland: a structural classification of forest types, maps of the forest mosaic, and estimates of spatial environmental variables. The ANN model characterizes the relative suitabilities of environments for 15 forest classes defined by their physiognomy and canopy structure. Inputs include seven climate variables, nine soil parent-material classes, and seven terrain variables. The data used to train the model consisted of a stratified random sample of 75000 points. Output of the model is used to measure the dissimilarity between the environment at each location and the environment that would be most suitable for the forest type that is mapped there. The model is highly successful at distinguishing the relative suitability of environments for the forest classes with 75% of the region's forest mosaic accurately predicted by the model at a one hectare resolution. In contrast, a comparable maximum likelihood classification has an accuracy of only 38%. In the remaining 25% of the region the environments are quite dissimilar to what would be expected for the forest types present there. This is especially the case at boundaries between forest classes and for a transitional forest class. Areas mapped as this disturbed, transitional class are generally classified by the model as having environments suitable to the forest type they are most likely to become. The approach has high potential for the analysis of climate change impacts as well as inferring vegetation patterns in the past and should be applicable wherever vegetation maps and spatial estimates of climate variables are available.     

Artificial neural network prediction of viruses in shellfish

A database was probed with artificial neural network (ANN) and multivariate logistic regression (MLR) models to investigate the efficacy of predicting PCR-identified human adenovirus (ADV), Norwalk-like virus (NLV), and enterovirus (EV) presence or absence in shellfish harvested from diverse countries in Europe (Spain, Sweden, Greece, and the United Kingdom). The relative importance of numerical and heuristic input variables to the ANN model for each country and for the combined data was analyzed with a newly defined relative strength effect, which illuminated the importance of bacteriophages as potential viral indicators. The results of this analysis showed that ANN models predicted all types of viral presence and absence in shellfish with better precision than MLR models for a multicountry database. For overall presence/absence classification accuracy, ANN modeling had a performance rate of 95.9%, 98.9%, and 95.7% versus 60.5%, 75.0%, and 64.6% for the MLR for ADV, NLV, and EV, respectively. The selectivity (prediction of viral negatives) was greater than the sensitivity (prediction of viral positives) for both models and with all virus types, with the ANN model performing with greater sensitivity than the MLR. ANN models were able to illuminate site-specific relationships between microbial indicators chosen as model inputs and human virus presence. A validation study on ADV demonstrated that the MLR and ANN models differed in sensitivity and selectivity, with the ANN model correctly identifying ADV presence with greater precision.     

Neural network-based segmentation and classification system for automated grading of histologic sections of bladder carcinoma

OBJECTIVE: To develop an image analysis system for automated nuclear segmentation and classification of histologic bladder sections employing quantitative nuclear features. STUDY DESIGN: Ninety-two cases were classified into three classes by experienced pathologists according to the WHO grading system: 18 cases as grade 1, 45 as grade 2, and 29 as grade 3. Nuclear segmentation was performed by means of an artificial neural network (ANN)-based pixel classification algorithm, and each case was represented by 36 nuclei features. Automated grading of bladder tumor histologic sections was performed by an ANN classifier implemented in a two-stage hierarchic tree. RESULTS: On average, 95% of the nuclei were correctly detected. At the first stage of the hierarchic tree, classifier performance in discriminating between cases of grade 1 and 2 and cases of grade 3 was 89%. At the second stage, 79% of grade 1 cases were correctly distinguished from grade 2 cases. CONCLUSION: The proposed image analysis system provides the means to reduce subjectivity in grading bladder tumors and may contribute to more accurate diagnosis and prognosis since it relies on nuclear features, the value of which has been confirmed.     

Principal component analysis and artificial neural network analysis of oral tissue fluorescence spectra: classification of normal premalignant and malignant pathological conditions

Pulsed laser-induced autofluorescence spectroscopic studies of pathologically certified normal, premalignant, and malignant oral tissues were carried out at 325 nm excitation. The spectral analysis and classification for discrimination among normal, premalignant, and malignant conditions were performed using principal component analysis (PCA) and artificial neural network (ANN) separately on the same set of spectral data. In case of PCA, spectral residuals, Mahalanobis distance, and scores of factors were used for discrimination among normal, premalignant, and malignant cases. In ANN, parameters like mean, spectral residual, standard deviation, and total energy were used to train the network. The ANN used in this study is a classical multiplayer feed-forward type with a back-propagation algorithm for the training of the network. The specificity and sensitivity were determined in both classification schemes. In the case of PCA, they are 100 and 92.9%, respectively, whereas for ANN they are 100 and 96.5% for the data set considered.     

Detection of dairy fouling: Combining ultrasonic measurements and classification methods

Fouling and cleaning in heat exchangers are severe and costly (up to 0.3% of gross national product) issues in dairy and food processing. Therefore, reducing cleaning time and cost is urgently needed. In this study, two classification methods [artificial neural network (ANN) and support vector machine (SVM)] for detecting protein and mineral fouling presence and absence based on ultrasonic measurements were presented and compared. ANN is based on a multilayer perceptron feed forward neural network, whereas SVM is based on clustering between fouling and no fouling using a hyperplane. When both fouling types (1239 datasets) were combined, ANN showed an accuracy of 71.9% while SVM displayed an accuracy of 97.6%. Separate fouling detection of mineral/protein fouling by ANN/SVM was comparable: dependent on fouling type detection accuracies of 100% (protein fouling, ANN and SVM), and 98.2% (SVM), and 93.5% (ANN) for mineral fouling was reached. It was shown that it was possible to detect fouling presence and absence offline in a static setup using ultrasonic measurements in combination with a classification method. This study proved the applicability of combining classification methods and fouling measurements to take a step toward reducing cleaning costs and time.     

Assignment of relevés to pre‐defined classes by supervised clustering of plant communities using a new composite index

Question: How does a newly designed method of supervised clustering perform in the assignment of relevé (species composition) data to a previously established classification. How do the results compare to the assignment by experts and to the assignment using a completely different numerical method? Material: Relevés analysed represent 4186 Czech grassland plots and 4990 plots from a wide variety of vegetation types (359 different associations or basal communities) in The Netherlands. For both data sets we had at our disposal an expert classification, and for the Czech data we also had available a numerical classification as well as a classification based on a neural network method (multi‐layer perceptron). Methods: Two distance indices, one qualitative and one quantitative, are combined into a single index by weighted multiplication. The composite index is a distance index for the dissimilarity between relevés and vegetation types. For both data sets the classifications by the new method were compared with the existing classifications. Results: For the Czech grasslands we correctly classified 81% of the plots to the classes of an expert classification at the alliance level and 71% to the classes of the numerical classification. Correct classification rates for the Dutch relevés were 64, 78 and 83 % for the lowest (subassociation or association), association, and alliance level, respectively. Conclusion: Our method performs well in assigning community composition records to previously established classes. Its performance is comparable to the performance of other methods of supervised clustering. Compared with a multi‐layer perceptron (a type of artificial neural network), fewer parameters have to be estimated. Our method does not need the original relevé data for the types, but uses synoptic tables. Another practical advantage is the provision of directly interpretable information on the contributions of separate species to the result.     

Classification of complete blood count and haemoglobin typing data by a C4.5 decision tree,a naïve Bayes classifier and a multilayer perceptron for thalassaemia screening

This article presents the classification of blood characteristics by a C4.5 decision tree, a naïve Bayes classifier and a multilayer perceptron for thalassaemia screening. The aim is to classify eighteen classes of thalassaemia abnormality, which have a high prevalence in Thailand, and one control class by inspecting data characterised by a complete blood count (CBC) and haemoglobin typing. Two indices namely a haemoglobin concentration (HB) and a mean corpuscular volume (MCV) are the chosen CBC attributes. On the other hand, known types of haemoglobin from six ranges of retention time identified via high performance liquid chromatography (HPLC) are the chosen haemoglobin typing attributes. The stratified 10-fold cross-validation results indicate that the best classification performance with average accuracy of 93.23% (standard deviation = 1.67%) and 92.60% (standard deviation = 1.75%) is achieved when the naïve Bayes classifier and the multilayer perceptron are respectively applied to samples which have been pre-processed by attribute discretisation. The results also suggest that the HB attribute is redundant. Moreover, the achieved classification performance is significantly higher than that obtained using only haemoglobin typing attributes as classifier inputs. Subsequently, the naïve Bayes classifier and the multilayer perceptron are applied to an additional data set in a clinical trial which respectively results in accuracy of 99.39% and 99.71%. These results suggest that a combination of CBC and haemoglobin typing analysis with a naïve Bayes classifier or a multilayer perceptron is highly suitable for automatic thalassaemia screening.     

PCA disjoint models for multiclass cancer analysis using gene expression data

MOTIVATION: Microarray expression profiling appears particularly promising for a deeper understanding of cancer biology and to identify molecular signatures supporting the histological classification schemes of neoplastic specimens. However, molecular diagnostics based on microarray data presents major challenges due to the overwhelming number of variables and the complex, multiclass nature of tumor samples. Thus, the development of marker selection methods, that allow the identification of those genes that are most likely to confer high classification accuracy of multiple tumor types, and of multiclass classification schemes is of paramount importance. RESULTS: A computational procedure for marker identification and for classification of multiclass gene expression data through the application of disjoint principal component models is described. The identified features represent a rational and dimensionally reduced base for understanding the basic biology of diseases, defining targets for therapeutic intervention, and developing diagnostic tools for the identification and classification of multiple pathological states. The method has been tested on different microarray data sets obtained from various human tumor samples. The results demonstrate that this procedure allows the identification of specific phenotype markers and can classify previously unseen instances in the presence of multiple classes.     

Non-linear models based on simple topological indices to identify RNase III protein members

Alignment-free classifiers are especially useful in the functional classification of protein classes with variable homology and different domain structures. Thus, the Topological Indices to BioPolymers (TI2BioP) methodology (Agüero-Chapin et al., 2010) inspired in both the TOPS-MODE and the MARCH-INSIDE methodologies allows the calculation of simple topological indices (TIs) as alignment-free classifiers. These indices were derived from the clustering of the amino acids into four classes of hydrophobicity and polarity revealing higher sequence-order information beyond the amino acid composition level. The predictability power of such TIs was evaluated for the first time on the RNase III family, due to the high diversity of its members (primary sequence and domain organization). Three non-linear models were developed for RNase III class prediction: Decision Tree Model (DTM), Artificial Neural Networks (ANN)-model and Hidden Markov Model (HMM). The first two are alignment-free approaches, using TIs as input predictors. Their performances were compared with a non-classical HMM, modified according to our amino acid clustering strategy. The alignment-free models showed similar performances on the training and the test sets reaching values above 90% in the overall classification. The non-classical HMM showed the highest rate in the classification with values above 95% in training and 100% in test. Although the higher accuracy of the HMM, the DTM showed simplicity for the RNase III classification with low computational cost. Such simplicity was evaluated in respect to HMM and ANN models for the functional annotation of a new bacterial RNase III class member, isolated and annotated by our group.     

Differentiation of probiotic and environmental Saccharomyces cerevisiae strains in animal feed

Aims: To establish an identification system for probiotic Saccharomyces cerevisiae strains based on artificial neural network (ANN)–assisted Fourier‐transform infrared (FTIR) spectroscopy to improve quality control of animal feed. Methods and Results: The ANN‐based system for differentiating environmental from probiotic S. cerevisiae strains comprises five authorized feed additive strains plus environmental strains isolated from different habitats. A total of 108 isolates were used as reference strains to create the ANN. DHPLC analysis and δ‐PCR were used as reference methods to type probiotic yeast isolates. The performance of the FTIR‐ANN was tested in an internal validation using unknown spectra of each reference strain. This validation step yielded a classification rate of 99·1 %. For an external validation, a test data set comprising 965 spectra of 63 probiotic and environmental S. cerevisiae isolates unknown to the ANN was used, resulting in a classification rate of 98·2 %. Conclusions: Our results demonstrate that probiotic S. cerevisiae strains in feed can be differentiated successfully from environmental isolates using both genotypic approaches and ANN‐based FTIR spectroscopy. Significance and Impact of the Study: FTIR‐based artificial neural network analysis provides a rapid and inexpensive technique for yeast identification both at the species and at the strain level in routine diagnostic laboratories, using a single sample preparation.     

Evolution of Filamentous Ascomycetes Inferred from LSU rDNA Sequence Data

Abstract: The nuclear LSU rRNA gene was examined in order to evaluate the current phylogeny of ascomycetes, which is mainly based on nuclear SSU rRNA data. Partial LSU rRNA gene sequences of 19 ascomycetes were determined and aligned with the corresponding sequences of 13 other ascomycetes retrieved from Genbank, including all classes traditionally distinguished and most of the recently accepted classes. The classification based on SSU rDNA data and morphological characters is supported, while the traditional classification and classifications based on the ascus type are rejected. Ascomycetes with perithecia and cleistothecia form monophyletic groups, while the discomycetes are a paraphyletic assemblage. The Pezizales are basal to all other filamentous ascomycetes. The monophyly of Loculoascomycetes is uncertain. The results of the LSU rDNA analysis agree with those of the SSU rDNA and RPB2 gene analyses, suggesting that most classes circumscribed in the filamentous ascomycetes are monophyletic. The branching order and relationships among these classes, however, cannot be elucidated with any of these data sets.     

Classification des stades de sommeil par des réseaux de neurones artificiels hiérarchiques

The goal of our work is to provide an automatic analysis and decision tool for sleep stages classification based on an artificial neural networks (ANN). The first difficulty lies in choosing the physiological signals representation and in particular the electroencephalogram (EEG). Once the representation adopted, the next step is to design the optimal neural network determined by a learning and validation process of data from a set of sleep records. We studied several configurations of conventional ANN giving results varying from 62 to 71 %, then we proposed a new hierarchical configuration, which gives a rate of 74 % correct classification for six stages. These results lead us to further explore this issue at the representation and design of ANNs to improve the performance of our tool.     

Artificial metaplasticity neural network applied to credit scoring

The assessment of the risk of default on credit is important for financial institutions. Different Artificial Neural Networks (ANN) have been suggested to tackle the credit scoring problem, however, the obtained error rates are often high. In the search for the best ANN algorithm for credit scoring, this paper contributes with the application of an ANN Training Algorithm inspired by the neurons' biological property of metaplasticity. This algorithm is especially efficient when few patterns of a class are available, or when information inherent to low probability events is crucial for a successful application, as weight updating is overemphasized in the less frequent activations than in the more frequent ones. Two well-known and readily available such as: Australia and German data sets has been used to test the algorithm. The results obtained by AMMLP shown have been superior to state-of-the-art classification algorithms in credit scoring.     

Identification of Relevant Phytochemical Constituents for Characterization and Authentication of Tomatoes by General Linear Model Linked to Automatic Interaction Detection (GLM-AID) and Artificial Neural Network Models (ANNs)

There are a large number of tomato cultivars with a wide range of morphological, chemical, nutritional and sensorial characteristics. Many factors are known to affect the nutrient content of tomato cultivars. A complete understanding of the effect of these factors would require an exhaustive experimental design, multidisciplinary scientific approach and a suitable statistical method. Some multivariate analytical techniques such as Principal Component Analysis (PCA) or Factor Analysis (FA) have been widely applied in order to search for patterns in the behaviour and reduce the dimensionality of a data set by a new set of uncorrelated latent variables. However, in some cases it is not useful to replace the original variables with these latent variables. In this study, Automatic Interaction Detection (AID) algorithm and Artificial Neural Network (ANN) models were applied as alternative to the PCA, AF and other multivariate analytical techniques in order to identify the relevant phytochemical constituents for characterization and authentication of tomatoes. To prove the feasibility of AID algorithm and ANN models to achieve the purpose of this study, both methods were applied on a data set with twenty five chemical parameters analysed on 167 tomato samples from Tenerife (Spain). Each tomato sample was defined by three factors: cultivar, agricultural practice and harvest date. General Linear Model linked to AID (GLM-AID) tree-structured was organized into 3 levels according to the number of factors. p-Coumaric acid was the compound the allowed to distinguish the tomato samples according to the day of harvest. More than one chemical parameter was necessary to distinguish among different agricultural practices and among the tomato cultivars. Several ANN models, with 25 and 10 input variables, for the prediction of cultivar, agricultural practice and harvest date, were developed. Finally, the models with 10 input variables were chosen with fit’s goodness between 44 and 100%. The lowest fits were for the cultivar classification, this low percentage suggests that other kind of chemical parameter should be used to identify tomato cultivars.     

Normalization of multicolor fluorescence in situ hybridization (M-FISH) images for improving color karyotyping.

BACKGROUND: Multiplex or multicolor fluorescence in situ hybridization (M-FISH) is a recently developed cytogenetic technique for cancer diagnosis and research on genetic disorders. By simultaneously viewing the multiply labeled specimens in different color channels, M-FISH facilitates the detection of subtle chromosomal aberrations. The success of this technique largely depends on the accuracy of pixel classification (color karyotyping). Improvements in classifier performance would allow the elucidation of more complex and more subtle chromosomal rearrangements. Normalization of M-FISH images has a significant effect on the accuracy of classification. In particular, misalignment or misregistration across multiple channels seriously affects classification accuracy. Image normalization, including automated registration, must be done before pixel classification. METHODS AND RESULTS: We studied several image normalization approaches that affect image classification. In particular, we developed an automated registration technique to correct misalignment across the different fluor images (caused by chromatic aberration and other factors). This new registration algorithm is based on wavelets and spline approximations that have computational advantages and improved accuracy. To evaluate the performance improvement brought about by these data normalization approaches, we used the downstream pixel classification accuracy as a measurement. A Bayesian classifier assumed that each of 24 chromosome classes had a normal probability distribution. The effects that this registration and other normalization steps have on subsequent classification accuracy were evaluated on a comprehensive M-FISH database established by Advanced Digital Imaging Research (http://www.adires.com/05/Project/MFISH_DB/MFISH_DB.shtml). CONCLUSIONS: Pixel misclassification errors result from different factors. These include uneven hybridization, spectral overlap among fluors, and image misregistration. Effective preprocessing of M-FISH images can decrease the effects of those factors and thereby increase pixel classification accuracy. The data normalization steps described in this report, such as image registration and background flattening, can significantly improve subsequent classification accuracy. An improved classifier in turn would allow subtle DNA rearrangements to be identified in genetic diagnosis and cancer research.     

Artificial neural networks for fly identification: A case study from the genera <Emphasis Type="Italic">Tachina</Emphasis> and <Emphasis Type="Italic">Ectophasia</Emphasis> (Diptera,Tachinidae)

The classification methodology based on morphometric data and supervised artificial neural networks (ANN) was tested on five fly species of the parasitoid genera Tachina and Ectophasia (Diptera, Tachinidae). Objects were initially photographed, then digitalized; consequently the picture was scaled and measured by means of an image analyser. The 16 variables used for classification included length of different wing veins or their parts and width of antennal segments. The sex was found to have some influence on the data and was included in the study as another input variable. Better and reliable classification was obtained when data from both the right and left wings were entered, the data from one wing were however found to be sufficient. The prediction success (correct identification of unknown test samples) varied from 88 to 100% throughout the study depending especially on the number of specimens in the training set. Classification of the studied Diptera species using ANN is possible assuming a sufficiently high number (tens) of specimens of each species is available for the ANN training. The methodology proposed is quite general and can be applied for all biological objects where it is possible to define adequate diagnostic characters and create the appropriate database.