Breathomics for Gastric Cancer Classification Using Back-propagation Neural Network.

Breathomics is the metabolomics study of exhaled air. It is a powerful emerging metabolomics research field that mainly focuses on health-related volatile organic compounds (VOCs). Since the quantity of these compounds varies with health status, breathomics assures to deliver noninvasive diagnostic tools. Thus, the main aim of breathomics is to discover patterns of VOCs related to abnormal metabolic processes occurring in the human body. Classification systems, however, are not designed for cost-sensitive classification domains. Therefore, they do not work on the gastric carcinoma (GC) domain where the benefit of correct classification of early stages is more than that of later stages, and also the cost of wrong classification is different for all pairs of predicted and actual classes. The aim of this work is to demonstrate the basic principles for the breathomics to classify the GC, for that the determination of VOCs such as acetone, carbon disulfide, 2-propanol, ethyl alcohol, and ethyl acetate in exhaled air and stomach tissue emission for the detection of GC has been analyzed. The breath of 49 GC and 30 gastric ulcer patients were collected for the study to distinguish the normal, suspected, and positive cases using back-propagation neural network (BPN) and produced the accuracy of 93%, sensitivity of 94.38%, and specificity of 89.93%. This study carries out the comparative study of the result obtained by the single- and multi-layer cascade-forward and feed-forward BPN with different activation functions. From this study, the multilayer cascade-forward outperforms the classification of GC from normal and benign cases.

Preparation of Curcumin Loaded Egg Albumin Nanoparticles Using Acetone and Optimization of Desolvation Process.

In this study, acetone was used as a desolvating agent to prepare the curcumin-loaded egg albumin nanoparticles. Response surface methodology was employed to analyze the influence of process parameters namely concentration (5-15%w/v) and pH (5-7) of egg albumin solution on solubility, curcumin loading and entrapment efficiency, nanoparticles yield and particle size. Optimum processing conditions obtained from response surface analysis were found to be the egg albumin solution concentration of 8.85%w/v and pH of 5. At this optimum condition, the solubility of 33.57%, curcumin loading of 4.125%, curcumin entrapment efficiency of 55.23%, yield of 72.85% and particles size of 232.6 nm were obtained and these values were related to the values which are predicted using polynomial model equations. Thus, the model equations generated for each response was validated and it can be used to predict the response values at any concentration and pH.

Assessment of the pathogenicity of cell-culture-adapted Newcastle disease virus strain Komarov.

Newcastle disease vaccines hitherto in vogue are produced from embryonated chicken eggs. Egg-adapted mesogenic vaccines possess several drawbacks such as paralysis and mortality in 2-week-old chicks and reduced egg production in the egg-laying flock. Owing to these possible drawbacks, we attempted to reduce the vaccine virulence for safe vaccination by adapting the virus in a chicken embryo fibroblast cell culture (CEFCC) system. Eighteen passages were carried out by CEFCC, and the pathogenicity was assessed on the basis of the mean death time, intracerebral pathogenicity index, and intravenous pathogenicity index, at equal passage intervals. Although the reduction in virulence demonstrated with increasing passage levels in CEFCC was encouraging, 20% of the 2-week-old birds showed paralytic symptoms with the virus vaccine from the 18(th)(final) passage. Thus, a tissue-culture-adapted vaccine would demand a few more passages by CEFCC in order to achieve a complete reduction in virulence for use as a safe and effective vaccine, especially among younger chicks. Moreover, it can be safely administered even to unprimed 8-week-old birds.

Unsupervised feature selection in digital mammogram image using rough set theory.

Feature Selection (FS) is a process which attempts to select features which are more informative. In this paper, a novel unsupervised FS in mammogram images, using rough set-based relative dependency measures, is proposed. A typical mammogram image processing system generally consists of mammogram image acquisition, pre-processing of image, segmentation and features extraction from the segmented mammogram image. The proposed unsupervised FS method is used to select features from data sets; the method is compared with existing rough set based supervised FS methods, and the classification performance of both methods are recorded and demonstrate the efficiency of this method.

Entropy based unsupervised Feature Selection in digital mammogram image using rough set theory.

Feature Selection (FS) is a process, which attempts to select features, which are more informative. In the supervised FS methods various feature subsets are evaluated using an evaluation function or metric to select only those features, which are related to the decision classes of the data under consideration. However, for many data mining applications, decision class labels are often unknown or incomplete, thus indicating the significance of unsupervised FS. However, in unsupervised learning, decision class labels are not provided. The problem is that not all features are important. Some of the features may be redundant, and others may be irrelevant and noisy. In this paper, a novel unsupervised FS in mammogram image, using rough set-based entropy measures, is proposed. A typical mammogram image processing system generally consists of mammogram image acquisition, pre-processing of image, segmentation, features extracted from the segmented mammogram image. The proposed method is used to select features from data set, the method is compared with the existing rough set-based supervised FS methods and classification performance of both methods are recorded and demonstrates the efficiency of the method.

Automatic detection of the breast border and nipple position on digital mammograms using genetic algorithm for asymmetry approach to detection of microcalcifications.

The presence of microcalcifications in breast tissue is one of the most incident signs considered by radiologist for an early diagnosis of breast cancer, which is one of the most common forms of cancer among women. In this paper, the Genetic Algorithm (GA) is proposed for automatic look at commonly prone area the breast border and nipple position to discover the suspicious regions on digital mammograms based on asymmetries between left and right breast image. The basic idea of the asymmetry approach is to scan left and right images are subtracted to extract the suspicious region. The proposed system consists of two steps: First, the mammogram images are enhanced using median filter, normalize the image, at the pectoral muscle region is excluding the border of the mammogram and comparing for both left and right images from the binary image. Further GA is applied to magnify the detected border. The figure of merit is calculated to evaluate whether the detected border is exact or not. And the nipple position is identified using GA. The some comparisons method is adopted for detection of suspected area. Second, using the border points and nipple position as the reference the mammogram images are aligned and subtracted to extract the suspicious region. The algorithms are tested on 114 abnormal digitized mammograms from Mammogram Image Analysis Society database.