Reduction of false positives in lung nodule detection using a two-level neural classification

The authors have developed a neural-digital computer-aided diagnosis system, based on a parameterized two-level convolution neural network (CNN) architecture and on a special multilabel output encoding procedure. The developed architecture was trained, tested, and evaluated specifically on the problem of diagnosis of lung cancer nodules found on digitized chest radiographs. The system performs automatic "suspect" localization, feature extraction, and diagnosis of a particular pattern-class aimed at a high degree of "true-positive fraction" detection and low "false-positive fraction" detection. In this paper, the authors aim at the presentation of the two-level neural classification method in reducing false-positives in their system. They employed receiver operating characteristics (ROC) method with the area under the ROC curve (A(z)) as the performance index to evaluate all the simulation results. The two-level CNN showed superior performance (A(z)=0.93) to the single-level CNN (A(z)=0.85). The proposed two-level CNN architecture is proven to be promising and to be extensible, problem-independent, and therefore, applicable to other medical or difficult diagnostic tasks in two-dimensional (2-D) image environments.     

对“微波共振跃迁法测量电子偶素2~3S_1-2~3P_1精细结构”实验拟合公式的探讨

本文对Michigan大学S.Hatamian等人在“微波共振跃迁法测量电子偶素2~3S_1-2~3P_J精细结构”实验中所用拟合公式进行了审慎的分析和推证,修正了该公式的功率增宽项,并就Mainz大学R.Ley等人对该公式的批评作了评价。最后,采用新、旧拟合公式对Michigan组实验数据进行拟合并讨论其结果。     

Thermal reaction of HNCO with NO2 at moderate temperatures

The thermal reaction of HNCO with NO₂ has been studied in the temperature range of 623 to 773 K by FTIR spectrometry. Major products measured are CO₂ and NO with a small amount of N₂O. Kinetic modeling of the time resolved concentration profiles of the reactants and products, aided by the thermochemical data of various likely reactive intermediates computed by means of the BAC-MP4 method, allows us to conclude that the reaction is initiated exclusively by a new bimolecular process: with a rate constant, k₁ = 2.5 × 10¹²e^?13,100/T cm³/mols. The well-known bimolecular reaction is the only strong competitive process in this important reactive system throughout the temperature range studied. Kinetic modeling of NO formation and NO₂ decay rates gave rise to values of k₁₀ which were in close agreement with literature data. © 1993 John Wiley & Sons, Inc.