The detection of lung cancer using massive artificial neural network based on soft tissue technique.

BACKGROUND: A proposed computer aided detection (CAD) scheme faces major issues during subtle nodule recognition. However, radiologists have not noticed subtle nodules in beginning stage of lung cancer while a proposed CAD scheme recognizes non subtle nodules using x-ray images. METHOD: Such an issue has been resolved by creating MANN (Massive Artificial Neural Network) based soft tissue technique from the lung segmented x-ray image. A soft tissue image recognizes nodule candidate for feature extortion and classification. X-ray images are downloaded using Japanese society of radiological technology (JSRT) image set. This image set includes 233 images (140 nodule x-ray images and 93 normal x-ray images). A mean size for a nodule is 17.8 mm and it is validated with computed tomography (CT) image. Thirty percent (42/140) abnormal represents subtle nodules and it is split into five stages (tremendously subtle, very subtle, subtle, observable, relatively observable) by radiologists. RESULT: A proposed CAD scheme without soft tissue technique attained 66.42% (93/140) sensitivity and 66.76% accuracy having 2.5 false positives per image. Utilizing soft tissue technique, many nodules superimposed by ribs as well as clavicles have identified (sensitivity is 72.85% (102/140) and accuracy is 72.96% at one false positive rate). CONCLUSION: In particular, a proposed CAD system determine sensitivity and accuracy in support of subtle nodules (sensitivity is 14/42 = 33.33% and accuracy is 33.66%) is statistically higher than CAD (sensitivity is 13/42 = 30.95% and accuracy is 30.97%) scheme without soft tissue technique. A proposed CAD scheme attained tremendously minimum false positive rate and it is a promising technique in support of cancerous recognition due to improved sensitivity and specificity.

Thermochemical conversion of raw and defatted algal biomass via hydrothermal liquefaction and slow pyrolysis.

Thermochemical conversion is a promising route for recovering energy from algal biomass. Two thermochemical processes, hydrothermal liquefaction (HTL: 300 °C and 10-12 MPa) and slow pyrolysis (heated to 450 °C at a rate of 50 °C/min), were used to produce bio-oils from Scenedesmus (raw and defatted) and Spirulina biomass that were compared against Illinois shale oil. Although both thermochemical conversion routes produced energy dense bio-oil (35-37 MJ/kg) that approached shale oil (41 MJ/kg), bio-oil yields (24-45%) and physico-chemical characteristics were highly influenced by conversion route and feedstock selection. Sharp differences were observed in the mean bio-oil molecular weight (pyrolysis 280-360 Da; HTL 700-1330 Da) and the percentage of low boiling compounds (bp<400 °C) (pyrolysis 62-66%; HTL 45-54%). Analysis of the energy consumption ratio (ECR) also revealed that for wet algal biomass (80% moisture content), HTL is more favorable (ECR 0.44-0.63) than pyrolysis (ECR 0.92-1.24) due to required water volatilization in the latter technique.

An evaluation of the colloidal stability of metal working fluid.

The effect of calcium on the stability of a commercial MWF is characterized through the experimental determination of the stability ratio, W. Three experimental methods of stability ratio evaluation are investigated. (1) The initial slope of the absorbance versus time curve is used to estimate the rate of coagulation. (2) Absorbance measurements are used to estimate N(0)/N with time. The stability ratio is determined from the slope of N(0)/N versus time. (3) Photon correlation spectroscopy (PCS) measurements of the volume distribution with time are used to estimate N(0)/N with time. Electrophoretic mobility was also measured and used to determine the fast coagulation concentration of the MWF. The accuracy of the experimentally determined stability ratios is evaluated using a population balance coagulation model. The model predicts the population distribution of a coagulating dispersion with time based on an initial particle size distribution and stability ratio. The model results were compared with the PCS-measured distributions to determine which stability ratio evaluation method best describes the stability of the MWF emulsion studied. Using the initial slope of the absorbance versus time curve to determine the fast coagulation concentration correlates well with electrophoretic mobility measurements. However, using absorbance measurements to determine the rate of coagulation underestimates the stability ratio of the MWF studied by orders of magnitude. N(0)/N values calculated from absorbance measurements provide a reasonable estimate of the stability ratio but inconsistencies in the method decrease its reliability. The stability ratio derived from PCS measurements appears to provide the most accurate, reliable description of MWF stability.