Pulmonary epithelium is known to undergo a preneoplastic process prior to the development of lung carcinoma. Squamous dysplasia and atypical adenomatous hyperplasia have been identified and classified as preinvasive lesions of squamous cell carcinoma and peripheral pulmonary adenocarcinoma, respectively. However, these commonly recognized preinvasive lesions do not completely explain the development of all histological types of lung carcinoma. By examining 114 resection lung specimens, we concluded that there are four histological patterns of bronchial epithelial dysplasia based on morphological features (basal cell dysplasia, columnar cell dysplasia, bronchial epithelial dysplasia with transitional differentiation, and squamous dysplasia). The histological patterns were further characterized by immunohistochemistry. Basal cell dysplasia was focally positive for cytokeratin (CK) 17 and 10/13; columnar cell dysplasia was generally positive for CK7, 8, and 18; bronchial epithelial dysplasia with transitional differentiation had a heterogeneous immunoprofile, while squamous dysplasia was positive for CK10/13 and focally positive for CK17. Various degrees of abnormal expression of p53 and Ki-67 were found in the different types of bronchial epithelial dysplasia. The cases were divided into three groups based on degree and extent of bronchial epithelial dysplasia. By Crosstabs McNemar test, the Mann-Whitney U-test (for two independent groups), the KruskalWallis one-way nonparametric ANOVA (for 42 independent groups) and Spearman correlation analysis, the degree and extent of bronchial epithelial dysplasia was shown to be positively correlated with the incidence of bronchogenic carcinoma and multifocal primary lung carcinoma (Po0.05). These findings indicated the following: (1) bronchial epithelium can develop various patterns of dysplasia with abnormal/ambiguous cell differentiation and abnormal expressions of p53 and Ki-67. Thus, these bronchial epithelial dysplastic lesions may represent a preneoplastic process. (2) The degree of bronchial epithelial dysplasia may significantly predispose individuals to bronchogenic carcinoma and multifocal primary lung carcinoma.

A tool condition monitoring system based on support vector machine and differential evolution is proposed in this article. In this system, support vector machine is used to realize the mapping between the extracted features and the tool wear states. At the same time, two important parameters of the support vector machine which are called penalty parameter C and kernel parameter [Formula: see text] are optimized simultaneously based on differential evolution algorithm. In order to verify the effectiveness of the proposed system, a multi-tooth milling experiment of titanium alloy was carried out. Cutting force signals related to different tool wear states were collected, and several time domain and frequency domain features were extracted to depict the dynamic characteristics of the milling process. Based on the extracted features, the differential evolution-support vector machine classifier is constructed to realize the tool wear classification. Moreover, to make a comparison, empirical selection method and four kinds of grid search algorithms are also used to select the support vector machine parameters. At the same time, cross validation is utilized to improve the robustness of the classifier evaluation. The results of analysis and comparisons show that the classification accuracy of differential evolution-support vector machine is higher than empirical selection-support vector machine. Moreover, the time consumption of differential evolution-support vector machine classifier is 5 to 12 times less than that of grid search-support vector machine.

Tool wear prediction is paramount for guaranteeing the quality of the workpiece and improving lifetime of the cutter. However, the multicollinearity between the extracted features deteriorates the prediction accuracy. To overcome this, a partial least square regression-based method is proposed. The main characteristic of partial least square regression is that the regression analysis is realized in the principle component space so that multicollinearity between the input variables can be avoided. To testify the correctness of the proposed method, the milling experiment is preceded and the dynamic cutting force is collected to depict the variation of the tool wear. Moreover, Monte Carlo cross validation is adopted to improve the robustness of partial least square regression. The analysis and comparison between the partial least square regression model and the multiple linear regression model shows that the presented method can get more accurate results.