Classification of breast masses using a committee machine of artificial neural networks

This work proposes a new approach using a committee machine of artificial neural networks to classify masses found in mammograms as benign or malignant. Three shape factors, three edge-sharpness measures, and 14 texture measures are used for the classification of 20 regions of interest (ROIs) related to malignant tumors and 37 ROIs related to benign masses. A group of multilayer perceptrons (MLPs) is employed as a committee machine of neural network classifiers. The classification results are reached by combining the responses of the individual classifiers. Experiments involving changes in the learning algorithm of the committee machine are conducted. The classification accuracy is evaluated using the area A. under the receiver operating characteristics (ROC) curve. The A, result for the committee machine is compared with the A, results obtained using MLPs and single-layer perceptrons (SLPs), as well as a linear discriminant analysis (LDA) classifier Tests are carried out using the student's t-distribution. The committee machine classifier outperforms the MLP SLP, and LDA classifiers in the following cases: with the shape measure of spiculation index, the A, values of the four methods are, in order 0.93, 0.84, 0.75, and 0.76; and with the edge-sharpness measure of acutance, the values are 0.79, 0.70, 0.69, and 0.74. Although the features with which improvement is obtained with the committee machines are not the same as those that provided the maximal value of A(z) (A(z) = 0.99 with some shape features, with or without the committee machine), they correspond to features that are not critically dependent on the accuracy of the boundaries of the masses, which is an important result. (c) 2008 SPIE and IS&T.

Photometric variability of the Be star CoRoT-ID 102761769

Context. Classical Be stars are rapid rotators of spectral type late O to early A and luminosity class V-III, which exhibit Balmer emission lines and often a near infrared excess originating in an equatorially concentrated circumstellar envelope, both produced by sporadic mass ejection episodes. The causes of the abnormal mass loss (the so-called Be phenomenon) are as yet unknown. Aims. For the first time, we can now study in detail Be stars outside the Earth's atmosphere with sufficient temporal resolution. We investigate the variability of the Be Star CoRoT-ID 102761769 observed with the CoRoT satellite in the exoplanet field during the initial run. Methods. One low-resolution spectrum of the star was obtained with the INT telescope at the Observatorio del Roque de los Muchachos. A time series analysis was performed using both cleanest and singular spectrum analysis algorithms to the CoRoT light curve. To identify the pulsation modes of the observed frequencies, we computed a set of models representative of CoRoT-ID 102761769 by varying its main physical parameters inside the uncertainties discussed. Results. We found two close frequencies related to the star. They are 2.465 c d(-1) (28.5 mu Hz) and 2.441 c d(-1) (28.2 mu Hz). The precision to which those frequencies were found is 0.018 c d(-1) (0.2 mu Hz). The projected stellar rotation was estimated to be 120 km s(-1) from the Fourier transform of spectral lines. If CoRoT-ID 102761769 is a typical Galactic Be star it rotates near the critical velocity. The critical rotation frequency of a typical B5-6 star is about 3.5 c d(-1) (40.5 mu Hz), which implies that the above frequencies are really caused by stellar pulsations rather than star's rotation.

Phosphoinositide-3 Kinase gamma Activity Contributes to Sepsis and Organ Damage by Altering Neutrophil Recruitment

Rationale Sepsis is a leading cause of death in the intensive care unit, characterized by a systemic inflammatory response (SIRS) and bacterial infection, which can often induce multiorgan damage and failure. Leukocyte recruitment, required to limit bacterial spread, depends on phosphoinositide-3 kinase gamma (PI3K gamma) signaling in vitro; however, the role of this enzyme in polymicrobial sepsis has remained unclear. Objectives: This study aimed to determine the specific role of the kinase activity of PI3K gamma in the pathogenesis of sepsis and multiorgan damage. Methods. PI3K gamma wild-type, knockout, and kinase-dead mice were exposed to cecal ligation and perforation induced sepsis and assessed for survival; pulmonary, hepatic, and cardiovascular damage; coagulation derangements; systemic inflammation; bacterial spread; and neutrophil recruitment. Additionally, wild-type mice were treated either before or after the onset of sepsis with a PI3K gamma inhibitor and assessed for survival, neutrophil recruitment, and bacterial spread. Measurements and Main Results: Both genetic and pharmaceutical PI3K gamma kinase inhibition significantly improved survival, reduced multiorgan damage, and limited bacterial decompartmentalization, while modestly affecting SIRS. Protection resulted from both neutrophil-independent mechanisms, involving improved cardiovascular function, and neutrophil-dependent mechanisms, through reduced susceptibility to neutrophil migration failure during severe sepsis by maintaining neutrophil surface expression of the chemokine receptor, CXCR2. Furthermore, PI3K gamma pharmacological inhibition significantly decreased mortality and improved neutrophil migration and bacterial control, even when administered during established septic shock. Conclusions: This study establishes PI3K gamma as a key molecule in the pathogenesis of septic infection and the transition from SIRS to organ damage and identifies it as a novel possible therapeutic target.