Efektivitas Penggunaan Seleksi Ciri CFS pada Klasifikasi Ciri Bentuk Nodul Kanker Payudara dengan Citra Ultrasonografi

The implementation of nodule shape characteristics is one of the parameters used in determining breast cancer malignancy. Mathematical calculations are used as a second decision to strengthen radiologists in determining breast cancer malignancy using ultrasound images (USG). The method used in this research is to filter ultrasound images that contain speckle noise, then continue the segmentation process, extracting shape features, selecting shape features, and classifying them. The feature selection process using Correlated based Feature Selection (CFS) is used to select the dominant shape features in the image. The classification results obtained show that the results of feature selection using CFS can improve the results of image accuracy, sensitivity and specificity, so as to be able to better distinguish the characteristic shape of the cancer nodule.

Shape analysis for classification of breast nodules on digital ultrasound images

<span>One of the imaging modalities for early detection of breast cancer malignancy is ultrasonography (USG). The malignancy can be analysed from the characteristic of nodule shape. This study aims to develop a method for classifying the shape of breast nodule into two classes, namely regular and irregular classes. The input image is pre-processed by using the combination of adaptive median filter and speckle reduction bilateral filtering (SRBF) to reduce speckle noises and to eliminate the image label. Afterwards, the filtered image is segmented based on active contour followed by feature extraction process. Nine extracted features, i.e. roundness, slimness and seven features of invariant moments, are used to classify nodule shape using multi-layer perceptron (MLP). The performance of the proposed method is evaluated using 105 breast nodule images which comprise of 57 regular and 48 irregular nodule images. The results of classification process achieve the level of accuracy, sensitivity and specificity at 96.20%, 97.90% and 94.70%, respectively. These results indicate that the proposed method successfully classifies the breast nodule images based on shape analysis.</span>

A Novel Approach for Computer-Aided Diagnosis for Distinction Between Benign and Malignant of Lung Nodules Based on Machine Learning Techniques

A new method is proposed to classify the lung nodules as benign and malignant. The method is based on analysis of lung nodule shape, contour, and texture for better classification. The data set consists of 39 lung nodules of 39 patients which contain 19 benign and 20 malignant nodules. Lung regions are segmented based on morphological operators and lung nodules are detected based on shape and area features. The proposed algorithm was tested on LIDC (lung image database consortium) datasets and the results were found to be satisfactory. The performance of the method for distinction between benign and malignant was evaluated by the use of receiver operating characteristic (ROC) analysis. The method achieved area under the ROC curve was 0.903 which reduces the false positive rate.

Multi-Scaling Homogenization Process for Nodular Cast Iron Using BEM

In this work, a multi-scaling homogenization process using boundary element formulation (BEM) for modeling a two-dimensional multi-phase microstructure containing irregular’s inclusions is presented. The BEM is very attractive for multiscale modeling tools for heterogeneous materials. In this approach, the iterative inhomogeneity discretization of the external boundary is disregarded, leading to a computational low cost. This approach was used for solving the elastic problem of a representative volume element (RVE) and the field theory medium. The main goal relies on finding the effective properties of micro-heterogeneous materials within a homogeneous and orthotropic matrix. Expressions for evaluating the effective properties under Plane Stress (PT) for orthotropic materials were also presented. Generally, the numerical models consider the graphite nodules as voids for GGG-40 and the roundness is close circular geometry. In this sense, a nodular cast iron GGG-40 microgram was obtained by X-ray computed tomography and Laser Confocal Microscope System, allowing the modeling of the true nodule shape. The numerical results showed good agreement with the experimental tests. The inclusions of graphite were considered as voids in the material matrix. Experimental stress–strain tests and micrographic analysis were used to determine the Young’s modulus, spatial distributions, as well as, nodule shape. The numerical in this work was compared with the obtained experimental results in this work. The comparison between the obtained experimental data with those available in the literature also showed good agreement.

Root system variability in common legumes in Central Europe

The aim of this study was to provide an overview of field measured root systems of common legume species growing under different environmental conditions in the Czech Republic. The plants, 214 individuals of 21 selected legume species from the tribes Galegeae (Astragalus glycyphyllos, Lupinus polyphyllus), Genisteae (Cytisus scoparius, Genista tinctoria), Loteae (Anthyllis vulneraria, Lotus corniculatus, Securigera varia), Trifolieae (Trifolium arvense, T. campestre, T. medium, T. pratense, T. repens) and Vicieae (Lathyrus pratensis, L. sylvestris, Vicia angustifolia, V. cracca, V. hirsuta), were collected using the monolith method from 27 sites.A rhizome was present in seven species and the maximum branching order was three for 15 species and five for five species. Recovery buds were recorded on the root system of eight species and woodiness was recorded in 11 species. Root diameter ranged from 1 to 12 mm — the minimum diameter was recorded in annuals and the maximum in perennials. The colour of the root system ranged from light to dark. In six species, young roots were light and older roots were dark. Globose, cylindrical, branched, fan-like and ruff-like nodules were recorded. Only one type of nodule shape was recorded in 11 species, two in seven species and three or four in three species. Nodules measured up to 2 mm in nine species, from 2 to 4 mm in three species and more than 4 mm in nine species. Legume root systems are highly variable and the variability was due to Raunkier’s life forms rather than membership of a tribe.